Home / microsoft / OmniParser
AI Slop Code RIsk Monitor

microsoft/OmniParser

A simple screen parsing tool towards pure vision based GUI agent

15.7 Elevated pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for microsoft/OmniParser, a Jupyter Notebook project with 25,509 GitHub stars. SynthScan examined 7,960 lines of code across 43 source files, recording 117 pattern matches distributed across 9 syntactic categories. The legacy adjusted pattern signal is 15.7 (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.

15.7
Adjusted Signal
15.7
Raw Pattern Score
100%
Time Factor
2026-07-20
Last Push
25.5K
Stars
Jupyter Notebook
Language
8.0K
Lines of Code
43
Files
117
Pattern Hits
2026-10-12
Scan Date
0.02
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 22.0/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 38 finding(s).

Hallucinated Dependency & Supply Chain Risk 32.7/100 · MEDIUM

Are imports declared and package/API names verified? 59 finding(s).

Agent Over-Engineering Ratio 17.3/100 · LOW

Are wrappers, guards, and repeated structures necessary? 30 finding(s).

PR Review Velocity Impact 61.0/100 · HIGH

Which changes need focused human review? 117 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

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.

Severity Breakdown

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.

CRITICAL 1HIGH 0MEDIUM 12LOW 104

Directory Score Breakdown

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.

Pattern Findings

The scanner identified 117 distinct pattern matches across 9 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.

Unused Imports58 hits · 58 pts
SeverityFileLineSnippetContext
LOWgradio_demo.py4CODE
LOWgradio_demo.py10CODE
LOWomnitool/gradio/app_streamlit.py7CODE
LOWomnitool/gradio/app_streamlit.py8CODE
LOWomnitool/gradio/app_streamlit.py21CODE
LOWomnitool/gradio/app_streamlit.py22CODE
LOWomnitool/gradio/app_streamlit.py24CODE
LOWomnitool/gradio/app_new.py9CODE
LOWomnitool/gradio/app_new.py16CODE
LOWomnitool/gradio/app_new.py16CODE
LOWomnitool/gradio/tools/screen_capture.py5CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py3CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py9CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py10CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py12CODE
LOWomnitool/gradio/agent/vlm_agent.py3CODE
LOWomnitool/gradio/agent/vlm_agent.py10CODE
LOWomnitool/gradio/agent/anthropic_agent.py4CODE
LOWomnitool/gradio/agent/anthropic_agent.py5CODE
LOWomnitool/gradio/agent/anthropic_agent.py9CODE
LOWomnitool/gradio/agent/anthropic_agent.py15CODE
LOWomnitool/gradio/agent/anthropic_agent.py15CODE
LOWomnitool/gradio/agent/anthropic_agent.py15CODE
LOWomnitool/gradio/agent/anthropic_agent.py15CODE
LOWomnitool/gradio/agent/anthropic_agent.py15CODE
LOWomnitool/gradio/agent/anthropic_agent.py24CODE
LOWomnitool/gradio/agent/anthropic_agent.py25CODE
LOWomnitool/gradio/agent/anthropic_agent.py25CODE
LOWomnitool/gradio/agent/anthropic_agent.py27CODE
LOWomnitool/gradio/agent/anthropic_agent.py29CODE
LOWomnitool/gradio/agent/anthropic_agent.py30CODE
LOWomnitool/gradio/agent/anthropic_agent.py31CODE
LOWomnitool/gradio/agent/anthropic_agent.py32CODE
LOWomnitool/gradio/agent/llm_utils/oaiclient.py1CODE
LOWomnitool/gradio/agent/llm_utils/oaiclient.py2CODE
LOWomnitool/gradio/agent/llm_utils/oaiclient.py3CODE
LOWutil/utils.py2CODE
LOWutil/utils.py6CODE
LOWutil/utils.py6CODE
LOWutil/utils.py7CODE
LOWutil/utils.py8CODE
LOWutil/utils.py10CODE
LOWutil/utils.py11CODE
LOWutil/utils.py13CODE
LOWutil/utils.py14CODE
LOWutil/utils.py15CODE
LOWutil/utils.py35CODE
LOWutil/utils.py36CODE
LOWutil/utils.py41CODE
LOWeval/ss_pro_gpt4o_omniv2.py7CODE
LOWeval/ss_pro_gpt4o_omniv2.py7CODE
LOWeval/ss_pro_gpt4o_omniv2.py7CODE
LOWeval/ss_pro_gpt4o_omniv2.py23CODE
LOWeval/ss_pro_gpt4o_omniv2.py34CODE
LOWeval/ss_pro_gpt4o_omniv2.py80CODE
LOWeval/ss_pro_gpt4o_omniv2.py80CODE
LOWeval/ss_pro_gpt4o_omniv2.py80CODE
LOWeval/ss_pro_gpt4o_omniv2.py81CODE
Excessive Try-Catch Wrapping20 hits · 22 pts
SeverityFileLineSnippetContext
LOW…tool/omnibox/vm/win11setup/setupscripts/server/main.py38 except Exception as e:CODE
LOWomnitool/gradio/app.py109 except Exception as e:STRING
LOWomnitool/gradio/app.py121 except Exception as e:STRING
LOWomnitool/gradio/app.py267 except Exception as e:STRING
MEDIUMomnitool/gradio/app.py258def get_header_image_base64():CODE
LOWomnitool/gradio/app_new.py132 except Exception as e:STRING
LOWomnitool/gradio/app_new.py144 except Exception as e:STRING
LOWomnitool/gradio/app_new.py307 except Exception as e:CODE
LOWomnitool/gradio/app_new.py418 except Exception as e:STRING
MEDIUMomnitool/gradio/app_new.py298def get_header_image_base64():CODE
LOWomnitool/gradio/tools/screen_capture.py28 except Exception as e:CODE
MEDIUMomnitool/gradio/agent/vlm_agent_with_orchestrator.py230 print(f"Error parsing: {vlm_response_json}")STRING
LOW⚡omnitool/gradio/agent/vlm_agent_with_orchestrator.py404 except Exception as e:STRING
MEDIUM⚡omnitool/gradio/agent/vlm_agent_with_orchestrator.py405 print(f"Error saving plan to {plan_path}: {str(e)}")STRING
MEDIUMomnitool/gradio/agent/vlm_agent.py167 print(f"Error parsing: {vlm_response_json}")CODE
LOWomnitool/gradio/agent/llm_utils/oaiclient.py60 except Exception as e:CODE
MEDIUMomnitool/gradio/agent/llm_utils/oaiclient.py61 print(f"Error in interleaved openAI: {e}. This may due to your invalid API key. Please check the response: {respCODE
LOWomnitool/gradio/agent/llm_utils/groqclient.py56 except Exception as e:CODE
MEDIUMomnitool/gradio/agent/llm_utils/groqclient.py57 print(f"Error in interleaved Groq: {e}")CODE
LOWomnitool/gradio/executor/anthropic_executor.py88 except Exception as e:CODE
Deep Nesting19 hits · 19 pts
SeverityFileLineSnippetContext
LOWomnitool/gradio/app_streamlit.py152CODE
LOWomnitool/gradio/loop.py40CODE
LOWomnitool/gradio/app.py353CODE
LOWomnitool/gradio/app_new.py311CODE
LOWomnitool/gradio/app_new.py470CODE
LOWomnitool/gradio/app_new.py619CODE
LOWomnitool/gradio/tools/computer.py108CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py451CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py66CODE
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py108CODE
LOWomnitool/gradio/agent/vlm_agent.py306CODE
LOWomnitool/gradio/agent/vlm_agent.py31CODE
LOWomnitool/gradio/agent/vlm_agent.py70CODE
LOWomnitool/gradio/agent/anthropic_agent.py116CODE
LOWomnitool/gradio/agent/llm_utils/oaiclient.py7CODE
LOWomnitool/gradio/agent/llm_utils/groqclient.py5CODE
LOWomnitool/gradio/executor/anthropic_executor.py74CODE
LOWutil/utils.py188CODE
LOWutil/utils.py241CODE
Self-Referential Comments5 hits · 8 pts
SeverityFileLineSnippetContext
MEDIUMomnitool/gradio/app_streamlit.py316 # Create a shareable text of the conversationSTRING
MEDIUMomnitool/gradio/app_streamlit.py324 # Create a download linkSTRING
MEDIUMomnitool/gradio/app.py184 # Create a concise version of the chatbot state for printingSTRING
MEDIUMomnitool/gradio/app_new.py217 # Create a concise version of the chatbot state for printingCOMMENT
MEDIUM⚡omnitool/gradio/agent/vlm_agent_with_orchestrator.py395 # Create a filename with timestampSTRING
Hyper-Verbose Identifiers9 hits · 7 pts
SeverityFileLineSnippetContext
LOW…tool/omnibox/vm/win11setup/setupscripts/server/main.py82def capture_screen_with_cursor():CODE
LOWomnitool/gradio/app_new.py691 def update_view_file_dropdown(uploaded_files):STRING
LOWomnitool/gradio/agent/vlm_agent_with_orchestrator.py451def _maybe_filter_to_n_most_recent_images(STRING
LOWomnitool/gradio/agent/vlm_agent.py306def _maybe_filter_to_n_most_recent_images(STRING
LOWomnitool/gradio/agent/anthropic_agent.py116def _maybe_filter_to_n_most_recent_images(STRING
LOWomnitool/gradio/executor/anthropic_executor.py74def _message_display_callback(messages):CODE
LOWomnitool/gradio/executor/anthropic_executor.py129def _maybe_prepend_system_tool_result(result: ToolResult, result_text: str):CODE
LOWutil/utils.py48def get_caption_model_processor(model_name, model_name_or_path="Salesforce/blip2-opt-2.7b", device=None):CODE
LOWeval/ss_pro_gpt4o_omniv2.py384def extract_first_bounding_box(text):CODE
Hallucination Indicators1 hit · 5 pts
SeverityFileLineSnippetContext
CRITICALomnitool/gradio/agent/anthropic_agent.py93 raw_response = self.client.beta.messages.with_raw_response.create(STRING
Redundant / Tautological Comments2 hits · 3 pts
SeverityFileLineSnippetContext
LOWomnitool/omnibox/vm/buildcontainer/install.sh38 # Check if the ISO was already processed by our scriptCOMMENT
LOWomnitool/omnibox/scripts/manage_vm.sh52# Check if control parameter is providedCOMMENT
Over-Commented Block2 hits · 2 pts
SeverityFileLineSnippetContext
LOWomnitool/omnibox/vm/buildcontainer/define.sh381# [ -f "$base" ] && return 0COMMENT
LOWomnitool/gradio/app_new.py181 # somehow can't display via gr.ImageCOMMENT
AI Structural Patterns1 hit · 1 pts
SeverityFileLineSnippetContext
LOWutil/utils.py417CODE