An autonomous agent that conducts deep research on any data using any LLM providers
This report summarizes scanner evidence for assafelovic/gpt-researcher, a Python project with 30,008 GitHub stars. SynthScan examined 99,709 lines of code across 702 source files, recording 1559 pattern matches distributed across 24 syntactic categories. The legacy adjusted pattern signal is 24.4 (Elevated pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 870 finding(s).
Are imports declared and package/API names verified? 273 finding(s).
Are wrappers, guards, and repeated structures necessary? 1008 finding(s).
Which changes need focused human review? 1559 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 1559 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | evals/quality_eval/metrics.py | 35 | def _extract_domains_from_text(text: str) -> set[str]: | CODE |
| LOW | gpt_researcher/prompts.py | 40 | def generate_mcp_tool_selection_prompt(query: str, tools_info: List[Dict], max_tools: int = 3) -> str: | CODE |
| LOW | gpt_researcher/prompts.py | 86 | def generate_mcp_research_prompt(query: str, selected_tools: List) -> str: | STRING |
| LOW | gpt_researcher/prompts.py | 122 | def generate_image_analysis_prompt( | CODE |
| LOW | gpt_researcher/prompts.py | 178 | def generate_image_prompt_enhancement( | CODE |
| LOW | gpt_researcher/prompts.py | 213 | def generate_search_queries_prompt( | CODE |
| LOW | gpt_researcher/prompts.py | 353 | def generate_resource_report_prompt( | STRING |
| LOW | gpt_researcher/prompts.py | 393 | def generate_custom_report_prompt( | CODE |
| LOW | gpt_researcher/prompts.py | 399 | def generate_outline_report_prompt( | CODE |
| LOW | gpt_researcher/prompts.py | 418 | def generate_deep_research_prompt( | CODE |
| LOW | gpt_researcher/prompts.py | 532 | def generate_quick_summary_prompt(query: str, context: str) -> str: | STRING |
| LOW | gpt_researcher/prompts.py | 573 | def generate_subtopics_prompt() -> str: | CODE |
| LOW | gpt_researcher/prompts.py | 596 | def generate_subtopic_report_prompt( | STRING |
| LOW | gpt_researcher/prompts.py | 673 | def generate_draft_titles_prompt( | STRING |
| LOW | gpt_researcher/prompts.py | 707 | def generate_report_introduction(question: str, research_summary: str = "", language: str = "english", report_format | STRING |
| LOW | gpt_researcher/prompts.py | 720 | def generate_report_conclusion(query: str, report_content: str, language: str = "english", report_format: str = "apa | STRING |
| LOW | gpt_researcher/prompts.py | 862 | def get_prompt_by_report_type( | CODE |
| LOW | gpt_researcher/agent.py | 639 | async def get_similar_written_contents_by_draft_section_titles( | CODE |
| LOW | gpt_researcher/scraper/scraper.py | 102 | def _looks_like_unextracted_pdf(text: str) -> bool: | CODE |
| LOW | gpt_researcher/scraper/utils.py | 142 | def does_tag_have_disallowed_class(elem) -> bool: | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 190 | def _visit_google_and_save_cookies(self): | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 206 | def scrape_text_with_selenium(self) -> tuple: | CODE |
| LOW⚡ | gpt_researcher/retrievers/utils.py | 110 | def get_plugin_retriever_names(): | CODE |
| LOW | gpt_researcher/retrievers/serper/serper.py | 33 | def _get_exclude_sites_from_env(self): | CODE |
| LOW | gpt_researcher/context/compression.py | 127 | def __get_contextual_retriever(self): | CODE |
| LOW | gpt_researcher/context/compression.py | 218 | def __get_contextual_retriever(self): | CODE |
| LOW⚡ | gpt_researcher/config/config.py | 77 | def _set_embedding_attributes(self) -> None: | CODE |
| LOW⚡ | gpt_researcher/config/config.py | 90 | def _handle_deprecated_attributes(self) -> None: | CODE |
| LOW | gpt_researcher/llm_provider/generic/base.py | 125 | def _reset_last_response_metadata(self) -> None: | CODE |
| LOW | gpt_researcher/llm_provider/generic/base.py | 129 | def _capture_response_metadata(self, message: Any) -> None: | CODE |
| LOW | gpt_researcher/utils/tools.py | 46 | async def create_chat_completion_with_tools( | CODE |
| LOW | gpt_researcher/utils/tools.py | 320 | def get_available_providers_with_tools() -> List[str]: | CODE |
| LOW | gpt_researcher/utils/costs.py | 111 | def _resolve_anthropic_model_name( | CODE |
| LOW | gpt_researcher/utils/costs.py | 180 | def _get_anthropic_pricing_multiplier( | CODE |
| LOW | gpt_researcher/mcp/research.py | 34 | async def conduct_research_with_tools(self, query: str, selected_tools: List) -> List[Dict[str, str]]: | CODE |
| LOW | gpt_researcher/mcp/tool_selector.py | 127 | async def _call_llm_for_tool_selection(self, prompt: str) -> str: | CODE |
| LOW | gpt_researcher/mcp/client.py | 41 | def convert_configs_to_langchain_format(self) -> Dict[str, Dict[str, Any]]: | CODE |
| LOW | gpt_researcher/vector_store/vector_store.py | 26 | def _create_langchain_documents(self, data: List[Dict[str, str]]) -> List[Document]: | CODE |
| LOW | gpt_researcher/actions/report_generation.py | 12 | async def write_report_introduction( | CODE |
| LOW | gpt_researcher/actions/report_generation.py | 160 | async def generate_draft_section_titles( | CODE |
| LOW | gpt_researcher/actions/markdown_processing.py | 85 | def generate_table_of_contents(headers, indent_level=0): | CODE |
| LOW | gpt_researcher/skills/context_manager.py | 38 | async def get_similar_content_by_query(self, query: str, pages: list) -> str: | CODE |
| LOW | gpt_researcher/skills/context_manager.py | 66 | async def get_similar_content_by_query_with_vectorstore(self, query: str, filter: dict | None) -> str: | CODE |
| LOW | gpt_researcher/skills/context_manager.py | 89 | async def get_similar_written_contents_by_draft_section_titles( | CODE |
| LOW | gpt_researcher/skills/context_manager.py | 121 | async def __get_similar_written_contents_by_query( | CODE |
| LOW⚡ | gpt_researcher/skills/researcher.py | 836 | async def _get_context_from_initial_results(self, query, query_domains, initial_results): | CODE |
| LOW⚡ | gpt_researcher/skills/researcher.py | 851 | async def _search_relevant_source_urls(self, query, query_domains: list | None = None, *, initial_results=None): | CODE |
| LOW | gpt_researcher/skills/researcher.py | 50 | async def _get_initial_search_results(self, query, query_domains=None): | CODE |
| LOW | gpt_researcher/skills/researcher.py | 265 | async def _get_context_by_vectorstore(self, query, filter: dict | None = None): | CODE |
| LOW | gpt_researcher/skills/researcher.py | 298 | async def _get_context_by_web_search(self, query, scraped_data: list | None = None, query_domains: list | None = Non | CODE |
| LOW | gpt_researcher/skills/researcher.py | 436 | async def _execute_mcp_research_for_queries(self, queries: list, mcp_retrievers: list) -> list: | CODE |
| LOW | gpt_researcher/skills/researcher.py | 492 | def _tavily_mcp_redundant_with_direct(self, mcp_retrievers, non_mcp_retrievers) -> bool: | CODE |
| LOW | gpt_researcher/skills/researcher.py | 739 | def _combine_mcp_and_web_context(self, mcp_context: list, web_context: str, sub_query: str) -> str: | CODE |
| LOW | gpt_researcher/skills/researcher.py | 792 | async def _process_sub_query_with_vectorstore(self, sub_query: str, filter: dict | None = None): | CODE |
| LOW | gpt_researcher/skills/deep_research.py | 77 | def parse_search_queries_response(response: str, num_queries: int) -> List[Dict[str, str]]: | CODE |
| LOW | gpt_researcher/skills/deep_research.py | 125 | def parse_follow_up_questions_response(response: str, num_questions: int) -> List[str]: | CODE |
| LOW | gpt_researcher/skills/deep_research.py | 149 | def parse_research_results_response(response: str, num_learnings: int) -> Dict[str, Any]: | CODE |
| LOW | gpt_researcher/skills/deep_research.py | 219 | def trim_context_to_word_limit(context_list: List[str], max_words: int = MAX_CONTEXT_WORDS) -> List[str]: | CODE |
| LOW | gpt_researcher/skills/image_generator.py | 270 | async def analyze_report_for_images( | CODE |
| LOW | gpt_researcher/skills/image_generator.py | 468 | async def generate_images_for_report( | CODE |
| 520 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | cli.py | 27 | # ============================================================================= | COMMENT |
| MEDIUM⚡ | cli.py | 29 | # ============================================================================= | COMMENT |
| MEDIUM⚡ | cli.py | 36 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 38 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 46 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 48 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 86 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 88 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 97 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 99 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 108 | # ===================================== | COMMENT |
| MEDIUM⚡ | cli.py | 110 | # ===================================== | COMMENT |
| MEDIUM | cli.py | 72 | # ===================================== | COMMENT |
| MEDIUM | cli.py | 74 | # ===================================== | COMMENT |
| MEDIUM | cli.py | 121 | # ===================================== | COMMENT |
| MEDIUM | cli.py | 123 | # ===================================== | COMMENT |
| MEDIUM | cli.py | 137 | # ============================================================================= | COMMENT |
| MEDIUM | cli.py | 139 | # ============================================================================= | COMMENT |
| MEDIUM | cli.py | 261 | # ============================================================================= | COMMENT |
| MEDIUM | cli.py | 263 | # ============================================================================= | COMMENT |
| MEDIUM | cli.py | 319 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | cli.py | 322 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | terraform/variables.tf | 171 | # ============================================================================== | COMMENT |
| MEDIUM | terraform/variables.tf | 173 | # ============================================================================== | COMMENT |
| MEDIUM | terraform/variables.tf | 203 | # ============================================================================== | COMMENT |
| MEDIUM | terraform/variables.tf | 205 | # ============================================================================== | COMMENT |
| MEDIUM⚡ | evals/quality_eval/metrics.py | 26 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/metrics.py | 28 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 64 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 66 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 130 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 132 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 169 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 171 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 299 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 301 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 388 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 390 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 542 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/metrics.py | 544 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 23 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 25 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 45 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 47 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 81 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 83 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 104 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 106 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 129 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/suite.py | 131 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 69 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 71 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 83 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 85 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 170 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 172 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/benchmark.py | 40 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/benchmark.py | 42 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/benchmark.py | 250 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | evals/quality_eval/benchmark.py | 252 | # --------------------------------------------------------------------------- | COMMENT |
| 44 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | cli.py | 204 | except Exception as e: | CODE |
| LOW | cli.py | 347 | except Exception as e: | CODE |
| LOW | cli.py | 356 | except Exception as e: | CODE |
| LOW⚡ | json_schema_generator.py | 28 | except Exception as e: | CODE |
| LOW | evals/hallucination_eval/run_eval.py | 188 | except Exception as e: | CODE |
| LOW | evals/hallucination_eval/evaluate.py | 51 | except Exception as e: | CODE |
| LOW | evals/quality_eval/run_eval.py | 56 | except Exception: | CODE |
| LOW | evals/quality_eval/run_eval.py | 129 | except Exception as e: | CODE |
| LOW | evals/quality_eval/run_eval.py | 216 | except Exception as e: | CODE |
| LOW | evals/quality_eval/run_eval.py | 319 | except Exception as e: | CODE |
| MEDIUM | evals/quality_eval/run_eval.py | 50 | def _get_git_commit() -> str: | CODE |
| LOW | evals/quality_eval/metrics.py | 246 | except Exception: | CODE |
| LOW | evals/quality_eval/metrics.py | 342 | except Exception: | CODE |
| LOW | evals/quality_eval/metrics.py | 362 | except Exception: | CODE |
| LOW | evals/quality_eval/metrics.py | 465 | except Exception: | CODE |
| LOW | evals/quality_eval/metrics.py | 493 | except Exception as e: | CODE |
| LOW | evals/quality_eval/suite.py | 154 | except Exception as e: | CODE |
| MEDIUM | evals/quality_eval/benchmark.py | 73 | def _get_git_commit() -> str: | CODE |
| LOW⚡ | evals/quality_eval/benchmark.py | 79 | except Exception: | CODE |
| LOW | evals/quality_eval/benchmark.py | 142 | except Exception: | CODE |
| LOW | evals/quality_eval/benchmark.py | 192 | except Exception as e: | CODE |
| LOW | evals/quality_eval/benchmark.py | 282 | except Exception as e: | CODE |
| LOW | evals/quality_eval/benchmark.py | 605 | except Exception as e: | CODE |
| LOW | evals/context_filter/collect.py | 52 | except Exception as e: | CODE |
| LOW | evals/context_filter/replay.py | 133 | except Exception as e: # e.g. the "none" context overflowing the model window | CODE |
| LOW | evals/simple_evals/run_eval.py | 34 | except Exception: | CODE |
| LOW | evals/simple_evals/run_eval.py | 142 | except Exception as e: | CODE |
| LOW | evals/simple_evals/run_eval.py | 244 | except Exception as e: | CODE |
| LOW | evals/simple_evals/run_eval.py | 258 | except Exception as e: | CODE |
| LOW | gpt_researcher/agent.py | 339 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/scraper.py | 272 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/utils.py | 61 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/utils.py | 118 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/pymupdf/pymupdf.py | 31 | except Exception: | CODE |
| LOW | gpt_researcher/scraper/pymupdf/pymupdf.py | 85 | except Exception as e: | CODE |
| MEDIUM | gpt_researcher/scraper/pymupdf/pymupdf.py | 86 | print(f"Error loading PDF : {self.link} {e}") | CODE |
| LOW | gpt_researcher/scraper/firecrawl/firecrawl.py | 98 | except Exception as img_err: | CODE |
| LOW | gpt_researcher/scraper/firecrawl/firecrawl.py | 103 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/beautiful_soup/beautiful_soup.py | 54 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/beautiful_soup/beautiful_soup.py | 71 | except Exception as e: | CODE |
| LOW⚡ | …_researcher/scraper/web_base_loader/web_base_loader.py | 45 | except Exception as e: | CODE |
| MEDIUM⚡ | …_researcher/scraper/web_base_loader/web_base_loader.py | 46 | print("Error extracting images/title! : " + str(e)) | CODE |
| LOW⚡ | …_researcher/scraper/web_base_loader/web_base_loader.py | 50 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 64 | except Exception as e: | CODE |
| MEDIUM | gpt_researcher/scraper/browser/browser.py | 65 | print(f"An error occurred during scraping: {str(e)}") | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 130 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 173 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/browser.py | 201 | except Exception as e: | CODE |
| MEDIUM | gpt_researcher/scraper/browser/browser.py | 76 | def _import_selenium(self): | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 55 | except Exception: | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 102 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 124 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 180 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 246 | except Exception as e: | CODE |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 259 | except Exception as e: | CODE |
| MEDIUM | gpt_researcher/scraper/browser/nodriver_scraper.py | 138 | def create_browser(): | CODE |
| LOW | gpt_researcher/scraper/tavily_extract/tavily_extract.py | 74 | except Exception as e: | CODE |
| LOW | gpt_researcher/retrievers/utils.py | 41 | except Exception as e: | CODE |
| LOW⚡ | gpt_researcher/retrievers/utils.py | 103 | except Exception as e: | CODE |
| LOW⚡ | gpt_researcher/retrievers/utils.py | 118 | except Exception as e: | CODE |
| 181 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | cli.py | 24 | CODE | |
| LOW | evals/hallucination_eval/run_eval.py | 16 | CODE | |
| LOW | evals/hallucination_eval/evaluate.py | 5 | CODE | |
| LOW | evals/hallucination_eval/evaluate.py | 6 | CODE | |
| LOW | evals/hallucination_eval/evaluate.py | 6 | CODE | |
| LOW | evals/hallucination_eval/evaluate.py | 8 | CODE | |
| LOW | evals/quality_eval/suite.py | 17 | CODE | |
| LOW | evals/quality_eval/base.py | 19 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 6 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 7 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 8 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 11 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 11 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 11 | CODE | |
| LOW | evals/simple_evals/simpleqa_eval.py | 12 | CODE | |
| LOW | gpt_researcher/__init__.py | 1 | CODE | |
| LOW | gpt_researcher/agent.py | 9 | CODE | |
| LOW | gpt_researcher/agent.py | 22 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 1 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 2 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 3 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 4 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 5 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 6 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 7 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 8 | CODE | |
| LOW | gpt_researcher/scraper/__init__.py | 9 | CODE | |
| LOW | …_researcher/scraper/web_base_loader/web_base_loader.py | 2 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 1 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 13 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 13 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 18 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 83 | CODE | |
| LOW | gpt_researcher/scraper/browser/nodriver_scraper.py | 8 | CODE | |
| LOW | gpt_researcher/scraper/browser/processing/html.py | 2 | CODE | |
| LOW | gpt_researcher/scraper/arxiv/arxiv.py | 7 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 1 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 2 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 3 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 4 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 5 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 6 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 7 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 8 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 9 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 10 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 11 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 12 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 13 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 14 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 15 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 16 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 17 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 18 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 19 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 20 | CODE | |
| LOW | gpt_researcher/retrievers/__init__.py | 21 | CODE | |
| LOW | gpt_researcher/retrievers/utils.py | 10 | CODE | |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 14 | CODE | |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 232 | CODE | |
| 196 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | README.md | 27 | The agent produces detailed, factual, and unbiased research reports with citations. GPT Researcher provides a full suite | CODE |
| MEDIUM | evals/hallucination_eval/run_eval.py | 130 | # Evaluate the research report for hallucination | COMMENT |
| MEDIUM | evals/hallucination_eval/run_eval.py | 192 | # Calculate hallucination rate | COMMENT |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 10 | "output": "# The Best Tutorials for Training LLMs on Custom Data: An In-Depth Report (2025)\n\nThe rapid evolution | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 17 | "source": "Source: https://www.globenewswire.com/news-release/2025/04/26/3068732/0/en/These-5-AI-trends-Will-Shape | CODE |
| MEDIUM | evals/quality_eval/run_eval.py | 111 | # --- LLM metric: hallucination (optional, requires `judges` library) --- | COMMENT |
| MEDIUM | evals/quality_eval/run_eval.py | 239 | # hallucination_rate: proportion of queries where hallucination was detected | COMMENT |
| MEDIUM | evals/quality_eval/run_eval.py | 248 | # TODO: hallucination detection itself might be wrong, need refinement | COMMENT |
| MEDIUM⚡ | evals/quality_eval/benchmark.py | 167 | return report, sources, context, None # multi-agent cost not easily tracked | CODE |
| MEDIUM | evals/quality_eval/requirements.txt | 5 | # Optional: hallucination metric only | COMMENT |
| MEDIUM | gpt_researcher/agent.py | 178 | # research run never needs an embedding model, or its credentials. | COMMENT |
| MEDIUM | gpt_researcher/skills/context_manager.py | 150 | # No usable embedding model (none configured, or its package or key | COMMENT |
| MEDIUM⚡ | tests/test_quality_metrics.py | 370 | # 6. evaluate_report (orchestration shared by run_eval + benchmark) | COMMENT |
| MEDIUM | …s/gpt-researcher/search-engines/test-your-retriever.md | 64 | "href": "https://accredianpublication.medium.com/building-smarter-systems-the-role-of-agentic-design-patterns-in-gen | CODE |
| MEDIUM | docs/docs/gpt-researcher/llms/llms.md | 63 | # specify the custom embedding model | COMMENT |
| MEDIUM | docs/docs/gpt-researcher/llms/running-with-azure.md | 14 | EMBEDDING="azure_openai:text-embedding-ada-002" # change to the deployment of your embedding model | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 31 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam, warehouse robotics / AMR)\n\n## Executive su | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 113 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. \n*Prepared July 5, 2026*\n\n## Executive summary\n\nVe | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 195 | "report": "# Due-Diligence Brief: Veltrix Dynamics B.V. \n**Topic:** Rotterdam-based warehouse robotics / AMR c | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 36 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 36 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 163 | "report": "# Cost-planning brief: OpenAI model lineup and API pricing for engineering selection (mid-2026)\n\nTh | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 208 | "report": "# Migration guide: upgrading a production app from Next.js 15 to current Next.js in mid-2026\n\n## Ex | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 59 | "report": "# Design brief: build a research assistant with the `deepagents` Python library\n\n## 1) Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 100 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 146 | "report": "# Cost-planning brief: OpenAI model lineup and API pricing for engineering selection (mid-2026)\n\nTh | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 146 | "report": "# Cost-planning brief: OpenAI model lineup and API pricing for engineering selection (mid-2026)\n\nTh | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 146 | "report": "# Cost-planning brief: OpenAI model lineup and API pricing for engineering selection (mid-2026)\n\nTh | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 187 | "report": "# Cost-planning brief: OpenAI model selection and API pricing (mid-2026)\n\nThis brief summarizes Ope | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 187 | "report": "# Cost-planning brief: OpenAI model selection and API pricing (mid-2026)\n\nThis brief summarizes Ope | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-29-57.json | 31 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n## Executive sum | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-05_14-29-57.json | 113 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nVeltrix Dynamics B.V. is a Ro | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-05_14-29-57.json | 195 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\n**Bottom line:** Veltrix Dyna | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 816 | "report": "# State of the stack, mid-2026\n## CTO briefing: AI + web engineering ecosystem\n\nThis briefing summ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 816 | "report": "# State of the stack, mid-2026\n## CTO briefing: AI + web engineering ecosystem\n\nThis briefing summ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 816 | "report": "# State of the stack, mid-2026\n## CTO briefing: AI + web engineering ecosystem\n\nThis briefing summ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 928 | "report": "# State of the stack, mid-2026: CTO briefing\n\nThis briefing summarizes where the AI application and | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 36 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 77 | "report": "# Design brief: building a research assistant with `deepagents` (Python)\n\n## 1) Executive summary\n | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing as of mid-2026\n\n## Executive summary\ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing as of mid-2026\n\n## Executive summary\ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing as of mid-2026\n\n## Executive summary\ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing as of mid-2026\n\n## Executive summary\ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing as of mid-2026\n\n## Executive summary\ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 163 | "report": "# Cost-planning brief: OpenAI API model selection and pricing (mid-2026)\n\n## Executive summary\n\nF | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 163 | "report": "# Cost-planning brief: OpenAI API model selection and pricing (mid-2026)\n\n## Executive summary\n\nF | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 163 | "report": "# Cost-planning brief: OpenAI API model selection and pricing (mid-2026)\n\n## Executive summary\n\nF | CODE |
| MEDIUM | …nts/benchmark_results/breadth_2026-07-04_22-44-58.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-04_22-22-39.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam) and its position in warehouse AMRs\n\n## Exe | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-04_22-22-39.json | 108 | "report": "# Due-Diligence Brief: Veltrix Dynamics B.V. \n**Subject:** Rotterdam-based warehouse robotics / AMR | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-04_22-06-28.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nI could **not verify that \u2 | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-04_22-06-28.json | 108 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nVeltrix Dynamics B.V. appears | CODE |
| 6 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 10 | "output": "# The Best Tutorials for Training LLMs on Custom Data: An In-Depth Report (2025)\n\nThe rapid evolution | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 10 | "output": "# The Best Tutorials for Training LLMs on Custom Data: An In-Depth Report (2025)\n\nThe rapid evolution | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 10 | "output": "# The Best Tutorials for Training LLMs on Custom Data: An In-Depth Report (2025)\n\nThe rapid evolution | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 16 | "output": "# Emerging Trends in Real-Time AI Evaluation Tools: A 2025 Analysis\n\nThe rapid integration of artific | CODE |
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 17 | "source": "Source: https://www.globenewswire.com/news-release/2025/04/26/3068732/0/en/These-5-AI-trends-Will-Shape | CODE |
| MEDIUM | gpt_researcher/prompts.py | 105 | return f"""You are a research assistant with access to specialized tools. Your task is to research the following | STRING |
| LOW | gpt_researcher/actions/web_scraping.py | 90 | # For now, we'll just return the raw HTML as a placeholder | COMMENT |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 31 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam, warehouse robotics / AMR)\n\n## Executive su | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 113 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. \n*Prepared July 5, 2026*\n\n## Executive summary\n\nVe | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-43-50.json | 113 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. \n*Prepared July 5, 2026*\n\n## Executive summary\n\nVe | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 36 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 77 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_19-10-24.json | 122 | "report": "# Cost-planning brief: OpenAI API model selection and pricing (mid-2026)\n\nThis brief summarizes Ope | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 59 | "report": "# Design brief: build a research assistant with the `deepagents` Python library\n\n## 1) Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 100 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM⚡ | …nts/benchmark_results/recency_2026-07-04_22-11-41.json | 146 | "report": "# Cost-planning brief: OpenAI model lineup and API pricing for engineering selection (mid-2026)\n\nTh | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-29-57.json | 31 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n## Executive sum | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-29-57.json | 31 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n## Executive sum | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 816 | "report": "# State of the stack, mid-2026\n## CTO briefing: AI + web engineering ecosystem\n\nThis briefing summ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 816 | "report": "# State of the stack, mid-2026\n## CTO briefing: AI + web engineering ecosystem\n\nThis briefing summ | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 928 | "report": "# State of the stack, mid-2026: CTO briefing\n\nThis briefing summarizes where the AI application and | CODE |
| MEDIUM⚡ | …nts/benchmark_results/breadth_2026-07-04_22-39-24.json | 928 | "report": "# State of the stack, mid-2026: CTO briefing\n\nThis briefing summarizes where the AI application and | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 36 | "report": "# Design brief: building a research assistant with the `deepagents` Python library\n\n## Executive su | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 77 | "report": "# Design brief: building a research assistant with `deepagents` (Python)\n\n## 1) Executive summary\n | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 335 | "report": "**Briefing: 2026 FIFA World Cup state of play, as of today**\n\n## Executive summary\n\nAs of **4 Jul | CODE |
| MEDIUM | …nts/benchmark_results/recency_2026-07-04_18-54-47.json | 335 | "report": "**Briefing: 2026 FIFA World Cup state of play, as of today**\n\n## Executive summary\n\nAs of **4 Jul | CODE |
| MEDIUM | …nts/benchmark_results/breadth_2026-07-04_22-44-58.json | 704 | "report": "# State of the stack, mid-2026\nA CTO briefing on the AI + web engineering ecosystem\n\n## Executive | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-04_22-22-39.json | 108 | "report": "# Due-Diligence Brief: Veltrix Dynamics B.V. \n**Subject:** Rotterdam-based warehouse robotics / AMR | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-04_22-06-28.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nI could **not verify that \u2 | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-04_22-06-28.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nI could **not verify that \u2 | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-37-31.json | 31 | "report": "## Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n### Executive s | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-05_14-37-31.json | 31 | "report": "## Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n### Executive s | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 79 | "report": "# How the Global Semiconductor Supply Chain Has Changed Since 2020, and the Key Dependencies and Risk | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 79 | "report": "# How the Global Semiconductor Supply Chain Has Changed Since 2020, and the Key Dependencies and Risk | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 115 | "report": "# What the Evidence Says About Remote Work, Productivity, and Employee Wellbeing\n\n## Executive summ | CODE |
| MEDIUM⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 160 | "report": "# AI governance in the US and EU: approaches and differences\n\n## Executive summary\n\nThe EU has ad | CODE |
| MEDIUM⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 169 | "report": "# AI Governance in the US and EU: How regulators are approaching it, and how the frameworks differ\n\ | CODE |
| MEDIUM⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 187 | "report": "# Report: The current state of mRNA vaccine technology beyond COVID-19, and the most promising applic | CODE |
| MEDIUM⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 196 | "report": "# What is the current state of mRNA vaccine technology beyond COVID-19, and which applications are mo | CODE |
| MEDIUM⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 196 | "report": "# What is the current state of mRNA vaccine technology beyond COVID-19, and which applications are mo | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 214 | "report": "# Economic and Environmental Arguments For and Against Deep-Sea Mining\n\n## Executive summary\n\nDee | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 214 | "report": "# Economic and Environmental Arguments For and Against Deep-Sea Mining\n\n## Executive summary\n\nDee | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 250 | "report": "# How precision agriculture is changing farming, and what evidence exists for its impact on yields an | CODE |
| MEDIUM | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 250 | "report": "# How precision agriculture is changing farming, and what evidence exists for its impact on yields an | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-04_22-16-55.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n## Executive sum | CODE |
| MEDIUM⚡ | …ents/benchmark_results/hybrid_2026-07-04_22-16-55.json | 26 | "report": "# Due-diligence brief: Veltrix Dynamics B.V. (Rotterdam warehouse robotics / AMR)\n\n## Executive sum | CODE |
| MEDIUM | …ents/benchmark_results/hybrid_2026-07-04_22-16-55.json | 108 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nVeltrix Dynamics B.V. appears | CODE |
| MEDIUM⚡ | deep_agents/benchmark_results/baseline_files_check.json | 19 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nVeltrix Dynamics B.V. appears, from | CODE |
| MEDIUM⚡ | deep_agents/benchmark_results/baseline_files_check.json | 19 | "report": "# Due-diligence brief: Veltrix Dynamics B.V.\n\n## Executive summary\n\nVeltrix Dynamics B.V. appears, from | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | gpt_researcher/retrievers/mcp/retriever.py | 234 | # Create a new event loop in a separate thread | COMMENT |
| MEDIUM⚡ | gpt_researcher/utils/logger.py | 19 | # Create a handler | COMMENT |
| MEDIUM⚡ | gpt_researcher/utils/logger.py | 22 | # Create a formatter using DefaultFormatter | COMMENT |
| MEDIUM | gpt_researcher/mcp/research.py | 236 | # Create a search result with a generic title | COMMENT |
| MEDIUM | gpt_researcher/skills/researcher.py | 768 | # Create a well-formatted context entry | COMMENT |
| MEDIUM | gpt_researcher/skills/image_generator.py | 606 | # Create a mapping of section headers to images | COMMENT |
| MEDIUM | tests/test-your-embeddings.py | 30 | # Create a Memory instance using the configuration | COMMENT |
| MEDIUM⚡ | tests/documents-report-source.py | 9 | # Define the report types to test | COMMENT |
| MEDIUM⚡ | tests/documents-report-source.py | 19 | # Define a common query and sources for testing | COMMENT |
| MEDIUM⚡ | tests/documents-report-source.py | 22 | # Define the output directory | COMMENT |
| MEDIUM⚡ | tests/documents-report-source.py | 33 | # Create an instance of GPTResearcher with report_source set to "documents" | COMMENT |
| MEDIUM⚡ | tests/documents-report-source.py | 41 | # Define the expected output filenames | COMMENT |
| MEDIUM⚡ | tests/report-types.py | 9 | # Define the report types to test | COMMENT |
| MEDIUM⚡ | tests/report-types.py | 12 | # Define a common query and sources for testing | COMMENT |
| MEDIUM⚡ | tests/report-types.py | 21 | # Create an instance of GPTResearcher | COMMENT |
| MEDIUM⚡ | tests/test-your-retriever.py | 11 | # Initialize the Config object | COMMENT |
| MEDIUM⚡ | tests/test-your-retriever.py | 18 | # Create a mock researcher object with necessary attributes | COMMENT |
| MEDIUM | tests/test-your-retriever.py | 32 | # Define a sub-query to test | COMMENT |
| MEDIUM⚡ | tests/test_security_fix.py | 157 | # Create a symlink pointing outside the directory | COMMENT |
| MEDIUM⚡ | tests/test_security_fix.py | 317 | # Create a subdirectory | COMMENT |
| MEDIUM | tests/test_security_fix.py | 123 | # Create a filename longer than 255 bytes | COMMENT |
| MEDIUM | tests/test_security_fix.py | 246 | # Create an existing file | COMMENT |
| MEDIUM | tests/test_security_fix.py | 287 | # Create a test file | COMMENT |
| MEDIUM | tests/vector-store.py | 127 | # Create an instance of GPTResearcher | STRING |
| MEDIUM | tests/test_researcher_logging.py | 26 | # Create a researcher instance with a logging-focused query | COMMENT |
| MEDIUM | backend/utils.py | 133 | # Create a document object | COMMENT |
| MEDIUM | backend/server/logging_config.py | 78 | # Create a function to get the logger and JSON handler | COMMENT |
| MEDIUM | backend/server/server_utils.py | 13 | # This module is imported under two different package names: as | COMMENT |
| MEDIUM | multi_agents/agents/utils/file_formats.py | 89 | # Create a document object | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | main.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | evals/hallucination_eval/run_eval.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | evals/hallucination_eval/evaluate.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/__init__.py | 3 | __all__ = ['GPTResearcher'] | CODE |
| LOW | gpt_researcher/agent.py | 777 | def set_verbose(self, verbose: bool) -> None: | CODE |
| LOW | gpt_researcher/scraper/__init__.py | 11 | __all__ = [ | CODE |
| LOW | gpt_researcher/scraper/beautiful_soup/beautiful_soup.py | 8 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/retrievers/__init__.py | 23 | __all__ = [ | CODE |
| LOW | gpt_researcher/retrievers/utils.py | 12 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 24 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/retrievers/mcp/__init__.py | 9 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/retrievers/brave/__init__.py | 3 | __all__ = ["BraveSearch"] | CODE |
| LOW | gpt_researcher/context/jev_filter.py | 30 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/context/__init__.py | 4 | __all__ = ['ContextCompressor', 'SearchAPIRetriever'] | CODE |
| LOW | gpt_researcher/context/select.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/config/config.py | 54 | def _set_attributes(self, config: Dict[str, Any]) -> None: | CODE |
| LOW⚡ | gpt_researcher/config/config.py | 77 | def _set_embedding_attributes(self) -> None: | CODE |
| LOW⚡ | gpt_researcher/config/config.py | 83 | def _set_llm_attributes(self) -> None: | CODE |
| LOW | gpt_researcher/config/config.py | 139 | def _set_doc_path(self, config: Dict[str, Any]) -> None: | CODE |
| LOW⚡ | gpt_researcher/config/config.py | 304 | def set_verbose(self, verbose: bool) -> None: | CODE |
| LOW | gpt_researcher/config/__init__.py | 5 | __all__ = ["Config", "BaseConfig", "DefaultConfig"] | CODE |
| LOW | gpt_researcher/llm_provider/__init__.py | 4 | __all__ = [ | CODE |
| LOW | gpt_researcher/llm_provider/image/__init__.py | 6 | __all__ = ["ImageGeneratorProvider", "ModelsLabImageGeneratorProvider"] | CODE |
| LOW | …archer/llm_provider/image/modelslab_image_generator.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/llm_provider/image/image_generator.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/llm_provider/generic/__init__.py | 3 | __all__ = ["GenericLLMProvider"] | CODE |
| LOW | gpt_researcher/utils/tools.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/utils/costs.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/mcp/research.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/mcp/tool_selector.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/mcp/client.py | 17 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/mcp/__init__.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/mcp/streaming.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/document/__init__.py | 5 | __all__ = ['DocumentLoader', 'OnlineDocumentLoader', 'LangChainDocumentLoader'] | CODE |
| LOW | gpt_researcher/vector_store/__init__.py | 3 | __all__ = ['VectorStoreWrapper'] | CODE |
| LOW | gpt_researcher/actions/retriever.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/actions/query_processing.py | 42 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/actions/__init__.py | 9 | __all__ = [ | CODE |
| LOW | gpt_researcher/actions/agent_creator.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/skills/context_manager.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/skills/__init__.py | 8 | __all__ = [ | CODE |
| LOW | gpt_researcher/skills/deep_research.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/skills/image_generator.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | gpt_researcher/skills/curator.py | 17 | logger = logging.getLogger(__name__) | CODE |
| LOW | tests/test_logging_output.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | tests/test_researcher_logging.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | tests/test_mcp.py | 32 | logger = logging.getLogger(__name__) | CODE |
| LOW | backend/chat/chat.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | backend/report_type/__init__.py | 4 | __all__ = [ | CODE |
| LOW | backend/report_type/deep_research/example.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | backend/server/server_utils.py | 39 | logger = logging.getLogger(__name__) | CODE |
| LOW | backend/server/app.py | 42 | logger = logging.getLogger(__name__) | CODE |
| LOW | backend/server/websocket_manager.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | multi_agents/__init__.py | 17 | __all__ = [ | CODE |
| LOW | multi_agents/memory/__init__.py | 4 | __all__ = [ | CODE |
| LOW | multi_agents/agents/__init__.py | 14 | __all__ = [ | CODE |
| LOW | multi_agents/ag2/agents/__init__.py | 11 | __all__ = [ | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …researcher/retrievers/pubmed_central/pubmed_central.py | 157 | # Step 1: Search for article IDs. Always return a list (never None): | COMMENT |
| LOW⚡ | …researcher/retrievers/pubmed_central/pubmed_central.py | 165 | # Step 2: Fetch full text for each article | COMMENT |
| LOW | gpt_researcher/skills/image_generator.py | 111 | # Step 1: Use LLM to identify best visualization opportunities | COMMENT |
| LOW | gpt_researcher/skills/image_generator.py | 126 | # Step 2: Generate all images in parallel | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 115 | // Step 1: Try to find it in localStorage first | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 134 | // Step 2: Try to find it in the backend | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 211 | // Step 3: If found in localStorage but not in backend, save it | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 256 | // Step 4: If not found anywhere, show not found message | COMMENT |
| LOW | .claude/references/adding-features.md | 22 | ### Step 1: Add Configuration | COMMENT |
| LOW | .claude/references/adding-features.md | 43 | ### Step 2: Create Provider | COMMENT |
| LOW | .claude/references/adding-features.md | 63 | ### Step 3: Create Skill | COMMENT |
| LOW | .claude/references/adding-features.md | 90 | ### Step 4: Integrate into Agent | COMMENT |
| LOW⚡ | .claude/references/adding-features.md | 109 | ### Step 5: Update Prompts | COMMENT |
| LOW⚡ | .claude/references/adding-features.md | 119 | ### Step 6: WebSocket Events | COMMENT |
| LOW⚡ | .claude/references/adding-features.md | 123 | ### Step 7: Frontend (if needed) | COMMENT |
| LOW⚡ | .claude/references/adding-features.md | 133 | ### Step 8: Documentation | COMMENT |
| LOW | .claude/references/retrievers.md | 78 | ### Step 1: Create Retriever File | COMMENT |
| LOW⚡ | .claude/references/retrievers.md | 101 | ### Step 2: Register in retriever.py | COMMENT |
| LOW⚡ | .claude/references/retrievers.md | 111 | ### Step 3: Export in __init__.py | COMMENT |
| LOW⚡ | .claude/references/retrievers.md | 120 | ### Step 4: Usage | COMMENT |
| LOW | docs/docs/gpt-researcher/context/data-ingestion.md | 44 | ### Step 1: Transform your content into Langchain Documents | COMMENT |
| LOW⚡ | docs/docs/gpt-researcher/context/data-ingestion.md | 93 | ### Step 2: Insert your Langchain Documents into a Langchain VectorStore | COMMENT |
| LOW | docs/docs/gpt-researcher/context/data-ingestion.md | 127 | ### Step 3: Pass your Langchain Vectorstore into your GPTR report | COMMENT |
| LOW⚡ | …ocs/gpt-researcher/getting-started/linux-deployment.md | 24 | ### Step 1: Update the System | COMMENT |
| LOW⚡ | …ocs/gpt-researcher/getting-started/linux-deployment.md | 29 | ### Step 2: Install Git | COMMENT |
| LOW⚡ | …ocs/gpt-researcher/getting-started/linux-deployment.md | 36 | ### Step 3: Install Docker | COMMENT |
| LOW⚡ | docs/blog/2024-09-7-hybrid-research/index.md | 129 | #### Step 1: Install GPT Researcher with PIP | COMMENT |
| LOW⚡ | docs/blog/2024-09-7-hybrid-research/index.md | 135 | #### Step 2: Setting up the environment | COMMENT |
| LOW⚡ | docs/blog/2024-09-7-hybrid-research/index.md | 144 | #### Step 3: Initialize GPT Researcher with hybrid research configuration | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | evals/quality_eval/metrics.py | 465 | except Exception: | CODE |
| HIGH | evals/quality_eval/benchmark.py | 142 | except Exception: | CODE |
| HIGH | gpt_researcher/scraper/pymupdf/pymupdf.py | 69 | except OSError: | CODE |
| HIGH | gpt_researcher/retrievers/mcp/retriever.py | 262 | except Exception: | CODE |
| HIGH | gpt_researcher/retrievers/mcp/retriever.py | 280 | except Exception: | CODE |
| HIGH | gpt_researcher/retrievers/mcp/retriever.py | 260 | except Exception: | CODE |
| HIGH | gpt_researcher/utils/llm.py | 109 | except json.JSONDecodeError: | CODE |
| HIGH | tests/test_empty_source_urls_notification.py | 62 | except Exception: | CODE |
| HIGH | tests/test_security_fix.py | 353 | except ValueError: | CODE |
| HIGH | backend/server/websocket_manager.py | 98 | except Exception: | CODE |
| HIGH | deep_agents/recency_benchmark.py | 236 | except json.JSONDecodeError: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | gpt_researcher/scraper/tavily_extract/tavily_extract.py | 43 | # failed_results may be missing, null, or a non-empty list. | COMMENT |
| HIGH | gpt_researcher/retrievers/xquik/xquik.py | 71 | # Use `or` fallbacks so an explicit JSON null ("tweets": null, | COMMENT |
| HIGH | gpt_researcher/retrievers/xquik/xquik.py | 72 | # "author": null, "text": null) does not slip a None past `.get()`'s | COMMENT |
| HIGH | …researcher/retrievers/pubmed_central/pubmed_central.py | 71 | # Error / unexpected envelopes may set esearchresult to null, | COMMENT |
| HIGH | tests/test_agent_creator_json_shape.py | 3 | json.loads / json_repair can return non-dicts (list, str, null) or dicts | STRING |
| HIGH | tests/test_xquik_null_fields.py | 7 | ``{"author": null}``. The subsequent ``author.get("username")`` / | STRING |
| HIGH | tests/test_mcp_tool_selector_json_repair.py | 64 | return '{"selected_tools":[null, {"index":0,"name":"a","reason":"r","relevance_score":1}],"selection_reasoning": | CODE |
| HIGH | tests/test_image_generator_json_repair.py | 64 | response = '{"suggestions":[null, "x", {"section_number":1,"image_prompt":"ok"}]}' | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | evals/hallucination_eval/run_eval.py | 146 | CODE | |
| LOW | evals/quality_eval/run_eval.py | 77 | CODE | |
| LOW | evals/quality_eval/benchmark.py | 487 | CODE | |
| LOW | evals/context_filter/replay.py | 68 | CODE | |
| LOW | evals/simple_evals/run_eval.py | 106 | CODE | |
| LOW | gpt_researcher/agent.py | 217 | CODE | |
| LOW | gpt_researcher/agent.py | 323 | CODE | |
| LOW | gpt_researcher/scraper/utils.py | 16 | CODE | |
| LOW | gpt_researcher/scraper/utils.py | 172 | CODE | |
| LOW | gpt_researcher/scraper/pymupdf/pymupdf.py | 34 | CODE | |
| LOW | gpt_researcher/scraper/browser/browser.py | 98 | CODE | |
| LOW | gpt_researcher/retrievers/searchapi/searchapi.py | 38 | CODE | |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 201 | CODE | |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 235 | CODE | |
| LOW | gpt_researcher/retrievers/serpapi/serpapi.py | 36 | CODE | |
| LOW | gpt_researcher/context/jev_filter.py | 84 | CODE | |
| LOW | gpt_researcher/config/config.py | 90 | CODE | |
| LOW | gpt_researcher/config/config.py | 253 | CODE | |
| LOW | gpt_researcher/llm_provider/image/image_generator.py | 268 | CODE | |
| LOW | gpt_researcher/llm_provider/image/image_generator.py | 351 | CODE | |
| LOW | gpt_researcher/llm_provider/generic/base.py | 146 | CODE | |
| LOW | gpt_researcher/utils/tools.py | 46 | CODE | |
| LOW | gpt_researcher/utils/tools.py | 230 | CODE | |
| LOW | gpt_researcher/utils/tools.py | 241 | CODE | |
| LOW | gpt_researcher/mcp/research.py | 34 | CODE | |
| LOW | gpt_researcher/mcp/research.py | 158 | CODE | |
| LOW | gpt_researcher/mcp/client.py | 41 | CODE | |
| LOW | gpt_researcher/mcp/streaming.py | 49 | CODE | |
| LOW | gpt_researcher/document/document.py | 22 | CODE | |
| LOW | gpt_researcher/actions/retriever.py | 150 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 97 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 298 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 436 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 520 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 739 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 851 | CODE | |
| LOW | gpt_researcher/skills/researcher.py | 975 | CODE | |
| LOW | gpt_researcher/skills/deep_research.py | 149 | CODE | |
| LOW | gpt_researcher/skills/image_generator.py | 468 | CODE | |
| LOW | gpt_researcher/skills/image_generator.py | 640 | CODE | |
| LOW | tests/test_empty_source_urls_notification.py | 94 | CODE | |
| LOW | backend/server/server_utils.py | 335 | CODE | |
| LOW | backend/server/websocket_manager.py | 30 | CODE | |
| LOW | backend/server/websocket_manager.py | 66 | CODE | |
| LOW | multi_agents/agents/human.py | 10 | CODE | |
| LOW | deep_agents/main.py | 40 | CODE | |
| LOW | deep_agents/recency_benchmark.py | 224 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | evals/hallucination_eval/evaluate.py | 66 | # Print results | COMMENT |
| LOW | gpt_researcher/scraper/firecrawl/firecrawl.py | 72 | # Check if the page has been scraped successfully | COMMENT |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 126 | # Check if we have any server configurations | COMMENT |
| LOW | gpt_researcher/retrievers/mcp/retriever.py | 214 | # Check if we have any server configurations | COMMENT |
| LOW | gpt_researcher/retrievers/mcp/__init__.py | 12 | # Check if langchain-mcp-adapters is available | COMMENT |
| LOW⚡ | gpt_researcher/utils/logger.py | 17 | # Check if the logger already has handlers to avoid duplicates | COMMENT |
| LOW | gpt_researcher/mcp/research.py | 84 | # Check if the LLM made tool calls | COMMENT |
| LOW | gpt_researcher/mcp/__init__.py | 16 | # Check if langchain-mcp-adapters is available | COMMENT |
| LOW | gpt_researcher/actions/query_processing.py | 66 | # Check if this is an MCP retriever and pass the researcher instance | COMMENT |
| LOW | gpt_researcher/actions/query_processing.py | 190 | # Check if MCP is the only retriever or one of multiple retrievers | COMMENT |
| LOW | gpt_researcher/skills/researcher.py | 139 | # Check if MCP retrievers are configured | COMMENT |
| LOW | gpt_researcher/skills/image_generator.py | 618 | # Check if this is a header that needs an image | COMMENT |
| LOW | tests/test-your-embeddings.py | 16 | # Check if embedding attributes are set | COMMENT |
| LOW⚡ | tests/documents-report-source.py | 45 | # Check if the PDF and DOCX files are created | COMMENT |
| LOW | tests/report-types.py | 36 | # Check if the report contains part of the query | COMMENT |
| LOW⚡ | backend/utils.py | 95 | # Set base_url to current directory for resolving any remaining relative paths | COMMENT |
| LOW | backend/chat/chat.py | 92 | # Check if Tavily client is available | COMMENT |
| LOW | backend/server/server_utils.py | 218 | # Check if ChatAgentWithMemory is available | COMMENT |
| LOW | .github/workflows/deploy.yml | 149 | # Check if commit contains application changes (non-terraform files) | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | README-ru_RU.md | 296 | export LANGCHAIN_API_KEY=your_api_key | CODE |
| HIGH | README.md | 321 | export LANGCHAIN_API_KEY=your_api_key | CODE |
| HIGH | frontend/nextjs/README.md | 80 | apiKey="your-api-key-if-needed" | CODE |
| HIGH | …s/docs/gpt-researcher/search-engines/search-engines.md | 69 | RETRIEVER_ARG_API_KEY=YOUR_API_KEY | CODE |
| HIGH | docs/docs/gpt-researcher/gptr/scraping.md | 109 | export TAVILY_API_KEY="your-api-key" | CODE |
| HIGH | docs/docs/proposals/social-media-data-acquisition.md | 586 | "Authorization": "Bearer YOUR_API_KEY", | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | gpt_researcher/utils/tools.py | 58 | Create a chat completion with tool calling support across all LLM providers. This function uses LangChain' | STRING |
| HIGH | gpt_researcher/utils/url_security.py | 61 | Validate that ``url`` is safe to fetch and return it unchanged. Args: url: The URL to validate. all | STRING |
| HIGH | multi_agents/agents/utils/utils.py | 4 | Sanitize a given filename by replacing characters that are invalid in Windows file paths with an underscore (' | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 160 | "report": "# AI governance in the US and EU: approaches and differences\n\n## Executive summary\n\nThe EU has ad | CODE |
| HIGH⚡ | …/benchmark_results/reports_2026-07-04_14-33-21_n8.json | 160 | "report": "# AI governance in the US and EU: approaches and differences\n\n## Executive summary\n\nThe EU has ad | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | gpt_researcher/skills/deep_research.py | 0 | previous research goal: {result['researchgoal']} follow-up questions: {' '.join(result['followupquestions'])} | STRING |
| HIGH | backend/report_type/deep_research/example.py | 0 | previous research goal: {result['researchgoal']} follow-up questions: {' '.join(result['followupquestions'])} | STRING |
| HIGH | docs/blog/2025-02-26-deep-research/index.md | 0 | previous research goal: {result['researchgoal']} follow-up questions: {' '.join(result['followupquestions'])} | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …researcher/retrievers/pubmed_central/pubmed_central.py | 157 | # Step 1: Search for article IDs. Always return a list (never None): | COMMENT |
| LOW⚡ | …researcher/retrievers/pubmed_central/pubmed_central.py | 165 | # Step 2: Fetch full text for each article | COMMENT |
| LOW | gpt_researcher/skills/image_generator.py | 111 | # Step 1: Use LLM to identify best visualization opportunities | COMMENT |
| LOW | gpt_researcher/skills/image_generator.py | 126 | # Step 2: Generate all images in parallel | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 115 | // Step 1: Try to find it in localStorage first | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 134 | // Step 2: Try to find it in the backend | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 211 | // Step 3: If found in localStorage but not in backend, save it | COMMENT |
| LOW | frontend/nextjs/app/research/[id]/page.tsx | 256 | // Step 4: If not found anywhere, show not found message | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | gpt_researcher/agent.py | 53 | CODE | |
| LOW | gpt_researcher/scraper/scraper.py | 158 | CODE | |
| LOW | gpt_researcher/retrievers/tavily/tavily_search.py | 65 | CODE | |
| LOW | gpt_researcher/utils/llm.py | 41 | CODE | |
| LOW | gpt_researcher/actions/report_generation.py | 209 | CODE | |
| LOW | backend/report_type/detailed_report/detailed_report.py | 11 | CODE | |
| LOW | backend/server/websocket_manager.py | 116 | CODE | |
| LOW | multi_agents/agents/fact_checker.py | 32 | CODE | |
| LOW | multi_agents/agents/orchestrator.py | 172 | CODE | |
| LOW | multi_agents/agents/writer.py | 71 | CODE | |
| LOW | multi_agents/agents/reviser.py | 52 | CODE | |
| LOW | multi_agents/agents/visualizer.py | 28 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | gpt_researcher/scraper/scraper.py | 81 | sentence_endings = sum(1 for ch in text if ch in _SENTENCE_ENDING_CHARS) | COMMENT |
| LOW | gpt_researcher/retrievers/duckduckgo/duckduckgo.py | 1 | from itertools import islice | COMMENT |
| LOW | gpt_researcher/retrievers/searx/searx.py | 1 | import os | COMMENT |
| LOW | gpt_researcher/document/online_document.py | 101 | # e.g. "pdf"/"docx") matches URLs that use upper-case extensions like | COMMENT |
| LOW | tests/research_test.py | 41 | print(f"\nLength of the context = {len(researcher.get_research_context())}") # Must say Non-zero value because the q | COMMENT |
| LOW | tests/research_test.py | 61 | # report, researcher = asyncio.run(get_report(query, report_type, sources)) | COMMENT |
| LOW | tests/research_test.py | 81 | # report_type = "research_report" | COMMENT |
| LOW | tests/research_test.py | 101 | COMMENT | |
| LOW | tests/test_security_fix.py | 21 | COMMENT | |
| LOW | .github/workflows/tests.yml | 141 | # runs an actual web-search research task ("latest updates in the NBA | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | evals/hallucination_eval/results/aggregate_results.json | 11 | "source": "Source: https://medium.com/@pranshu.singh765/mastering-llm-custom-data-training-in-2025-fine-tuning-lar | CODE |
| LOW | gpt_researcher/prompts.py | 311 | - Don't forget to add a reference list at the end of the report in {report_format} format. | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | json_schema_generator.py | 35 | "name": "John Doe", | CODE |
| LOW | docs/docs/gpt-researcher/llms/llms.md | 48 | OPENAI_API_KEY=dummy_key | CODE |
| LOW | docs/docs/gpt-researcher/llms/llms.md | 61 | OPENAI_API_KEY=dummy_key | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | json_schema_generator.py | 31 | # Example usage | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | deep_agents/drb_generate.py | 103 | async def run_task(task: dict, agent=agent, system=system): | CODE |
| LOW | deep_agents/recency_benchmark.py | 282 | async def run_task(task: dict) -> dict: | CODE |