GreyDGL/PentestGPT

21.4

Adjusted Score

21.4

Raw Score

100%

Time Factor

2026-07-14

Last Push

14.2K

Stars

Python

Language

20.6K

Lines of Code

146

Files

373

Pattern Hits

2026-07-14

Scan Date

0.03

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 4MEDIUM 15LOW 354

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 373 distinct pattern matches across 15 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. 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 diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers217 hits · 242 pts

Severity	File	Line	Snippet	Context
LOW	pentestgpt_agent/tests/test_episode.py	135	async def test_successful_episode_is_recoverable_from_its_trace(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	172	async def test_provider_crash_leaves_a_complete_failure_trace(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	195	async def test_reasoning_and_raw_provider_payloads_are_never_persisted(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	227	async def test_operational_events_and_terminal_result_share_one_ordered_trace(	CODE
LOW	pentestgpt_agent/tests/test_episode.py	264	async def test_episode_trace_and_wrapper_monitor_accept_live_operational_events(	CODE
LOW	pentestgpt_agent/tests/test_episode.py	326	async def test_missing_terminal_event_is_an_explicit_episode_failure(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	349	async def test_trace_load_preserves_events_before_a_torn_jsonl_tail(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	372	async def test_trace_records_the_provider_configuration_that_shaped_the_episode(	CODE
LOW	pentestgpt_agent/tests/test_episode.py	414	def test_claude_safety_rejection_has_a_typed_informative_failure() -> None:	CODE
LOW	pentestgpt_agent/tests/test_episode.py	448	def test_existing_provider_stop_reasons_remain_typed() -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	66	def test_valid_supervisor_decision_atomically_adds_and_leases_one_task(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	104	def test_discovered_url_path_is_inside_its_authorized_origin(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	141	def test_url_scope_rejects_targets_outside_the_authorized_origin(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	183	def test_url_subtree_scope_rejects_prefix_and_ambiguous_path_escapes(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	214	def test_supervisor_cannot_create_a_speculative_task_backlog(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	241	def test_new_task_must_be_selected_immediately_instead_of_deferred(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	307	def test_unknown_basis_observation_is_rejected(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	336	def test_basis_producer_must_be_a_dependency(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	402	def test_exploit_requires_the_latest_test_evidence_on_the_same_surface(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	478	def test_exploit_provenance_requires_the_exact_test_target_including_query(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	522	def test_supervisor_cannot_finish_while_work_is_open(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	566	def test_finish_requires_an_explicit_existing_canonical_basis(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	625	def test_finish_basis_must_come_from_a_completed_task(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_plan.py	694	def test_test_task_cannot_embed_exploitation_as_its_objective(	CODE
LOW	pentestgpt_agent/tests/test_plan.py	727	def test_plan_text_and_reference_collections_are_bounded(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_local_benchmark.py	185	async def test_local_template_injection_benchmark_reaches_a_grounded_flag(	CODE
LOW	pentestgpt_agent/tests/test_dependency.py	8	def test_unified_agent_is_loaded_from_the_external_dependency() -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	37	def _latest_observation_basis(prompt: str) -> list[str]:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	539	async def test_one_grounded_task_can_drive_a_run_to_completion(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	602	async def test_max_turn_failure_after_an_action_is_atomically_terminal(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	667	async def test_provider_failure_before_actions_retries_once_in_the_same_run(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	722	async def test_malformed_result_after_an_action_is_a_terminal_validation_failure(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	773	async def test_uncaptured_done_evidence_degrades_to_grounded_progress_and_retries(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	833	async def test_reopening_a_completed_run_does_not_invoke_a_provider(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	900	async def test_restart_commits_a_completed_executor_trace_without_replaying_it(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	982	async def test_restart_retries_a_failed_executor_trace_only_when_it_has_no_actions(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1068	async def test_restart_recovers_a_terminal_executor_event_when_output_write_was_interrupted(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1153	async def test_restart_retries_when_crash_created_only_the_executor_episode_directory(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1221	async def test_restart_commits_a_completed_supervisor_trace_without_replaying_it(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1281	async def test_invalid_supervisor_plan_retries_in_a_new_logged_episode(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1325	async def test_exhausted_supervisor_contract_failures_settle_the_run(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1376	async def test_decision_limit_atomically_settles_the_run(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1424	async def test_known_structured_transport_failure_is_recovered_without_replaying_actions(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1470	async def test_exact_result_at_max_turns_is_recovered_without_replaying_actions(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1516	async def test_earlier_grounded_result_is_recovered_after_ungrounded_retry(	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1560	async def test_decision_budget_is_persistent_across_process_restart(tmp_path: Path) -> None:	CODE
LOW	pentestgpt_agent/tests/test_loop.py	1640	async def test_restart_settles_a_malformed_trace_without_leaving_an_active_lease(	CODE
LOW	pentestgpt_agent/tests/test_execution.py	18	def test_transport_recovery_skips_a_later_incomplete_done_candidate() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	56	def test_transport_recovery_accepts_only_an_exact_executor_contract() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	110	def test_executor_cannot_complete_from_an_uncaptured_evidence_claim() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	153	def test_executor_can_complete_by_exactly_reusing_same_task_evidence() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	202	def test_executor_cannot_reuse_evidence_from_another_task() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	247	def test_paraphrased_prior_evidence_degrades_without_creating_an_observation() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	291	def test_actionful_attempt_cannot_degrade_an_unresolved_prior_evidence_quote() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	338	def test_whitespace_equivalent_text_is_not_an_exact_evidence_quote() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	379	def test_crlf_transport_normalization_resolves_to_the_exact_receipt_slice() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	419	def test_exact_ordered_lines_widen_to_one_contiguous_receipt_span() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	467	def test_line_span_widening_rejects_reordered_receipt_lines() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	506	def test_exact_unique_line_envelope_recovers_a_rich_reordered_quote() -> None:	CODE
LOW	pentestgpt_agent/tests/test_execution.py	568	def test_canonical_execution_fields_have_conservative_size_limits() -> None:	CODE
157 more matches not shown…

Unused Imports85 hits · 76 pts

Severity	File	Line	Context
LOW	pentestgpt_legacy/smoke_test.py	13	CODE
LOW	pentestgpt_legacy/config.py	9	CODE
LOW	pentestgpt_legacy/config.py	11	CODE
LOW	pentestgpt_legacy/config.py	11	CODE
LOW	pentestgpt_legacy/test_connection.py	8	CODE
LOW	pentestgpt_legacy/__init__.py	9	CODE
LOW	pentestgpt_legacy/main.py	10	CODE
LOW	pentestgpt_legacy/llm/config.py	9	CODE
LOW	pentestgpt_legacy/llm/registry.py	14	CODE
LOW	pentestgpt_legacy/llm/client.py	10	CODE
LOW	pentestgpt_legacy/llm/__init__.py	11	CODE
LOW	pentestgpt_legacy/llm/__init__.py	12	CODE
LOW	pentestgpt_legacy/llm/__init__.py	12	CODE
LOW	pentestgpt_legacy/llm/__init__.py	13	CODE
LOW	pentestgpt_legacy/llm/__init__.py	13	CODE
LOW	pentestgpt_legacy/llm/__init__.py	13	CODE
LOW	pentestgpt_legacy/llm/__init__.py	13	CODE
LOW	pentestgpt_legacy/llm/factory.py	3	CODE
LOW	pentestgpt_legacy/llm/base.py	9	CODE
LOW	pentestgpt_legacy/llm/providers/openai_compatible.py	12	CODE
LOW	pentestgpt_legacy/llm/providers/__init__.py	3	CODE
LOW	pentestgpt_legacy/llm/providers/__init__.py	4	CODE
LOW	pentestgpt_legacy/llm/providers/__init__.py	5	CODE
LOW	pentestgpt_legacy/llm/providers/anthropic_provider.py	8	CODE
LOW	pentestgpt_legacy/llm/providers/gemini_provider.py	9	CODE
LOW	pentestgpt_legacy/utils/pentest_gpt.py	15	CODE
LOW	pentestgpt_agent/tests/test_local_benchmark.py	1	CODE
LOW	pentestgpt_agent/tests/support/local_target.py	1	CODE
LOW	pentestgpt_agent/tests/live/test_local_model.py	1	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/plan.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trace.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trial.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/execution.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/audit.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/memory.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/identifiers.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/agents.py	3	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/loop.py	3	CODE
LOW	unified_agent/task.py	3	CODE
LOW	unified_agent/skills.py	10	CODE
LOW	unified_agent/events.py	3	CODE
LOW	unified_agent/tools.py	15	CODE
LOW	unified_agent/__init__.py	7	CODE
LOW	unified_agent/__init__.py	7	CODE
LOW	unified_agent/__init__.py	7	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	8	CODE
LOW	unified_agent/__init__.py	21	CODE
LOW	unified_agent/__init__.py	21	CODE
LOW	unified_agent/__init__.py	21	CODE
LOW	unified_agent/__init__.py	21	CODE
25 more matches not shown…

Decorative Section Separators10 hits · 30 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	63	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	65	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	77	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	79	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	115	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	117	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	131	# ============================================================================	COMMENT
MEDIUM	pyproject.toml	133	# ============================================================================	COMMENT
MEDIUM	tests/conftest.py	5	# =============================================================================	COMMENT
MEDIUM	tests/conftest.py	7	# =============================================================================	COMMENT

Modern Structural Boilerplate15 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	pentestgpt_legacy/config.py	22	__all__ = [	CODE
LOW	pentestgpt_legacy/__init__.py	11	__all__ = ["__version__"]	CODE
LOW	pentestgpt_legacy/llm/__init__.py	15	__all__ = [	CODE
LOW	pentestgpt_legacy/llm/providers/__init__.py	7	__all__ = ["AnthropicProvider", "GeminiProvider", "OpenAICompatibleProvider"]	CODE
LOW	pentestgpt_agent/tests/support/local_target.py	94	__all__ = ["LocalTarget", "local_template_target"]	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/plan.py	335	__all__ = [	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trace.py	427	__all__ = [	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trial.py	366	__all__ = ["TrialConfig", "main", "run_trial"]	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/execution.py	385	__all__ = [	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/audit.py	447	__all__ = ["audit_run", "main"]	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/memory.py	986	__all__ = [	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/identifiers.py	18	__all__ = ["validate_opaque_id"]	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/agents.py	628	__all__ = [	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/loop.py	314	__all__ = ["PentestLoop"]	CODE
LOW	unified_agent/__init__.py	41	__all__ = [	CODE

Cross-Language Confusion3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	tests/docker/test_container_health.py	89	result = self._exec_in_container(running_container, "test -d /workspace && echo ok")	CODE
HIGH	tests/docker/test_container_health.py	125	running_container, "which nc \|\| which netcat \|\| which ncat"	CODE
HIGH	tests/docker/test_container_health.py	168	result = self._exec_in_container(running_container, "which claude \|\| echo 'not found'")	CODE

Redundant / Tautological Comments7 hits · 13 pts

Severity	File	Line	Snippet	Context
LOW⚡	setup.sh	29	# Check if Docker is installed	COMMENT
LOW⚡	setup.sh	36	# Check if Docker is running	COMMENT
LOW⚡	setup.sh	45	# Check if Claude Code is installed (not strictly required since it's in Docker)	COMMENT
LOW	fix-workspace-permissions.sh	14	# Check if workspace exists	COMMENT
LOW	tests/docker/test_container_health.py	46	# Check if container is running	COMMENT
LOW	scripts/entrypoint.sh	30	# Check if template exists	COMMENT
LOW	scripts/entrypoint.sh	61	# Check if CCR is running by testing the port	COMMENT

Excessive Try-Catch Wrapping10 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	pentestgpt_legacy/smoke_test.py	54	except Exception as e:	CODE
LOW	pentestgpt_legacy/main.py	135	except Exception as e:	CODE
LOW	pentestgpt_legacy/utils/pentest_gpt.py	161	except Exception as e:	CODE
LOW	pentestgpt_legacy/utils/pentest_gpt.py	425	except Exception as e:	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trace.py	257	except Exception as exc: # provider failures become a durable failed result	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trial.py	170	except Exception as exc:	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trial.py	188	except Exception:	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/trial.py	355	except Exception:	CODE
LOW	unified_agent/agent.py	198	except Exception as e:	CODE
LOW	unified_agent/backends/codex.py	288	except Exception as e: # JSON-RPC / transport errors from the SDK	CODE

Fake / Example Data7 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_agent.py	20	def __init__(self, events=None, delay=0.0, fail_with=None, fake_name="fake"):	CODE
LOW	tests/test_agent.py	21	self.name = fake_name	CODE
LOW⚡	tests/test_agent.py	82	backend = FakeBackend(events=GOOD_EVENTS, fake_name="codex")	CODE
LOW⚡	tests/test_agent.py	162	backend=FakeBackend(events=GOOD_EVENTS, delay=0.2, fake_name="a"), workspace=tmp_path / "wa"	CODE
LOW⚡	tests/test_agent.py	165	backend=FakeBackend(events=GOOD_EVENTS, delay=0.2, fake_name="b"), workspace=tmp_path / "wb"	CODE
LOW⚡	tests/test_agent.py	178	backend=FakeBackend(events=GOOD_EVENTS, fake_name="a"), workspace=tmp_path / "wa"	CODE
LOW⚡	tests/test_agent.py	181	backend=FakeBackend(events=GOOD_EVENTS, fake_name="b"), workspace=tmp_path / "wb"	CODE

Deep Nesting9 hits · 9 pts

Severity	File	Line	Context
LOW	pentestgpt_legacy/utils/pentest_gpt.py	207	CODE
LOW	pentestgpt_legacy/utils/pentest_gpt.py	262	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/audit.py	64	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/memory.py	431	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/loop.py	83	CODE
LOW	pentestgpt_agent/src/pentestgpt_agent/loop.py	184	CODE
LOW	unified_agent/backends/codex.py	133	CODE
LOW	unified_agent/backends/codex.py	191	CODE
LOW	unified_agent/backends/claude_code.py	129	CODE

Dead Code4 hits · 8 pts

Severity	File	Line	Context
MEDIUM	pentestgpt_agent/tests/test_episode.py	64	CODE
MEDIUM	pentestgpt_agent/tests/test_loop.py	282	CODE
MEDIUM	pentestgpt_agent/tests/test_loop.py	307	CODE
MEDIUM	pentestgpt_agent/tests/test_trial.py	139	CODE

Synthetic Comment Markers1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	.agents/skills/triage/SKILL.md	16	> This was generated by AI during triage.	CODE

Modern AI Meta-Vocabulary1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	pentestgpt_legacy/utils/pentest_gpt.py	81	# Chunk size for parsing, scaled to the reasoning model's context window.	COMMENT

Over-Commented Block2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	…s/skills/diagnosing-bugs/scripts/hitl-loop.template.sh	1	#!/usr/bin/env bash	COMMENT
LOW	scripts/docker-login.sh	1	#!/usr/bin/env bash	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	…s/skills/diagnosing-bugs/scripts/hitl-loop.template.sh	6	# Usage:	COMMENT

AI Structural Patterns1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	unified_agent/agent.py	105		CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings