toolbox-governance · Nerlo

AI review of these findings

Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.

Upheld as real: 421
Dismissed as false positives: 61
Not reviewed: 214

Out of 696 findings across every scanner that examined this package. 23 of 60 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 214 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.

32 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SKILL-003, AAK-SKILL-001, opt.nerlo-rules.nerlo-install-pipe-to-shell and 2 more · Files: Tool/everything-claude-code/docs/zh-TW/skills/golang-patterns/SKILL.md, Tool/everything-claude-code/docs/zh-TW/skills/security-review/SKILL.md, Tool/everything-claude-code/docs/zh-TW/skills/backend-patterns/SKILL.md and 28 more · reported by agent-audit-kit, nerlo-install-instruction
21 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-IPI-WILD-CORPUS-001, secrets-claude-md-env-25667, secrets-claude-md-env-25791 and 15 more · Files: Tool/Skill_Seekers/CLAUDE.md, Tool/Skill_Seekers/docs/PRODUCTION_DEPLOYMENT.md, Tool/Skill_Seekers/docs/TROUBLESHOOTING.md and 1 more · reported by agent-audit-kit, agentshield
8 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SECRET-004, AAK-MCP-ARGV-TOCTOU-001, AAK-SSRF-002 and 2 more · Files: Tool/cocos-mcp-server/tests/bug-fixes.test.ts, Tool/Skill_Seekers/tests/test_utilities.py, Tool/Skill_Seekers/tests/test_upload_skill.py and 4 more · reported by agent-audit-kit

In installed code — never dismissed

These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.

71 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/KI/Error_Book/entries/ERR-116__payload-embedded-identity-desyncs-from-credential.md, /repo/KI/External_KI/skills/devops/devops.md and 31 more · reported by nerlo-install-instruction
48 AAK-SECRET-004
Files: KI/.obsidian/plugins/obsidian-local-rest-api/data.json, KI/.obsidian/plugins/tag-wrangler/main.js, KI/.obsidian/plugins/templater-obsidian/main.js and 22 more · reported by agent-audit-kit
29 AAK-MCP-ATTEST-001
Files: Agent/mcp/profiles/codebase-memory.mcp.json, Agent/mcp/profiles/cocos-creator.mcp.json, Agent/mcp/profiles/unity.mcp.json and 3 more · reported by agent-audit-kit
22 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/Agent/guides/setup/linux.md, /repo/Agent/index/skill_registry.json, /repo/Agent/mcp/deploy_guide.md and 8 more · reported by nerlo-install-instruction
19 AAK-LEGAL-002
Files: package.json, Tool/cocos-mcp-server/package.json, Tool/superpowers/package.json and 16 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

4 AAK-LOGINJ-001
Files: Tool/unity-mcp/Server/src/services/tools/run_tests.py · reported by agent-audit-kit

Not reviewed

130 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: mcp-risky-filesystem, mcp-risky-browserbase, mcp-risky-browser-use and 127 more · Files: Tool/everything-claude-code/mcp-configs/mcp-servers.json, Tool/everything-claude-code/commands/instinct-export.md, Tool/everything-claude-code/commands/loop-status.md and 59 more · reported by agentshield
82 The review budget for this scan was already spent before these findings were reached.
Rules: skills-missing-governance-Tool/everything-claude-code/commands/learn-eval.md, skills-missing-telemetry-Tool/everything-claude-code/commands/model-route.md, skills-missing-governance-Tool/everything-claude-code/commands/checkpoint.md and 40 more · Files: Tool/everything-claude-code/commands/learn-eval.md, Tool/everything-claude-code/commands/model-route.md, Tool/everything-claude-code/commands/checkpoint.md and 47 more · reported by agentshield, nerlo-install-instruction, nerlo-behavioral
2 The model did not answer for these findings.
Rules: opt.nerlo-rules.nerlo-install-fetch-raw-then-run · Files: /repo/Tool/Skill_Seekers/docs/KUBERNETES_DEPLOYMENT.md, /repo/Tool/everything-claude-code/docs/zh-CN/skills/autonomous-loops/SKILL.md · reported by nerlo-install-instruction

What the review concluded

Artifact has critical vulnerabilities including remote code execution and credential exposure.

The artifact contains critical vulnerabilities that allow for remote code execution via SQL in `gemini.py` and `cloud_storage_cli.py`. It also exposes credentials in `s3_storage.py` and has multiple instances of server-side request forgery in `server_fastmcp.py`. Additionally, the artifact defines skills that can execute external commands and has configurations for multi-cloud platform interactions that warrant attention.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-MCP-001 · Agent/mcp/profiles/cocos-creator.mcp.json · critical · reported by agent-audit-kit
AAK-MCP-001 · Agent/mcp/profiles/unity.mcp.json · critical · reported by agent-audit-kit
AAK-LLM-SQL-RCE-001 · Tool/Skill_Seekers/src/skill_seekers/cli/adaptors/gemini.py · critical · reported by agent-audit-kit
AAK-LLM-SQL-RCE-001 · Tool/Skill_Seekers/src/skill_seekers/cli/cloud_storage_cli.py · critical · reported by agent-audit-kit
AAK-MCP-015 · Tool/Skill_Seekers/src/skill_seekers/cli/generate_router.py · critical · reported by agent-audit-kit
AAK-SECRET-003 · Tool/Skill_Seekers/src/skill_seekers/cli/storage/s3_storage.py · critical · reported by agent-audit-kit
· · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

Scan history

2 scans on record. Every scan's full results are retained immutably for 24 months.

Completed	Composite	Change	Scanners	Status
Sep 3, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source ·n/a: not applicable	rejected
Aug 4, 2026	Scan Halted	—	agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable	rejected

Per-scanner history:

AI review of these findings

Upheld as real: 421
Dismissed as false positives: 61
Not reviewed: 214

Out of 696 findings across every scanner that examined this package. 23 of 60 findings rated critical by their scanner were among the dismissals.

Not reviewed is not the same as clean. Those 214 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.

Why those were dismissed

32 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SKILL-003, AAK-SKILL-001, opt.nerlo-rules.nerlo-install-pipe-to-shell and 2 more · Files: Tool/everything-claude-code/docs/zh-TW/skills/golang-patterns/SKILL.md, Tool/everything-claude-code/docs/zh-TW/skills/security-review/SKILL.md, Tool/everything-claude-code/docs/zh-TW/skills/backend-patterns/SKILL.md and 28 more · reported by agent-audit-kit, nerlo-install-instruction
21 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-IPI-WILD-CORPUS-001, secrets-claude-md-env-25667, secrets-claude-md-env-25791 and 15 more · Files: Tool/Skill_Seekers/CLAUDE.md, Tool/Skill_Seekers/docs/PRODUCTION_DEPLOYMENT.md, Tool/Skill_Seekers/docs/TROUBLESHOOTING.md and 1 more · reported by agent-audit-kit, agentshield
8 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SECRET-004, AAK-MCP-ARGV-TOCTOU-001, AAK-SSRF-002 and 2 more · Files: Tool/cocos-mcp-server/tests/bug-fixes.test.ts, Tool/Skill_Seekers/tests/test_utilities.py, Tool/Skill_Seekers/tests/test_upload_skill.py and 4 more · reported by agent-audit-kit

In installed code — never dismissed

71 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/KI/Error_Book/entries/ERR-116__payload-embedded-identity-desyncs-from-credential.md, /repo/KI/External_KI/skills/devops/devops.md and 31 more · reported by nerlo-install-instruction
48 AAK-SECRET-004
Files: KI/.obsidian/plugins/obsidian-local-rest-api/data.json, KI/.obsidian/plugins/tag-wrangler/main.js, KI/.obsidian/plugins/templater-obsidian/main.js and 22 more · reported by agent-audit-kit
29 AAK-MCP-ATTEST-001
Files: Agent/mcp/profiles/codebase-memory.mcp.json, Agent/mcp/profiles/cocos-creator.mcp.json, Agent/mcp/profiles/unity.mcp.json and 3 more · reported by agent-audit-kit
22 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/Agent/guides/setup/linux.md, /repo/Agent/index/skill_registry.json, /repo/Agent/mcp/deploy_guide.md and 8 more · reported by nerlo-install-instruction
19 AAK-LEGAL-002
Files: package.json, Tool/cocos-mcp-server/package.json, Tool/superpowers/package.json and 16 more

Upheld — the review declined to dismiss these

The model could have called any of these a false positive and did not.

4 AAK-LOGINJ-001
Files: Tool/unity-mcp/Server/src/services/tools/run_tests.py · reported by agent-audit-kit

Not reviewed

130 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: mcp-risky-filesystem, mcp-risky-browserbase, mcp-risky-browser-use and 127 more · Files: Tool/everything-claude-code/mcp-configs/mcp-servers.json, Tool/everything-claude-code/commands/instinct-export.md, Tool/everything-claude-code/commands/loop-status.md and 59 more · reported by agentshield
82 The review budget for this scan was already spent before these findings were reached.
Rules: skills-missing-governance-Tool/everything-claude-code/commands/learn-eval.md, skills-missing-telemetry-Tool/everything-claude-code/commands/model-route.md, skills-missing-governance-Tool/everything-claude-code/commands/checkpoint.md and 40 more · Files: Tool/everything-claude-code/commands/learn-eval.md, Tool/everything-claude-code/commands/model-route.md, Tool/everything-claude-code/commands/checkpoint.md and 47 more · reported by agentshield, nerlo-install-instruction, nerlo-behavioral
2 The model did not answer for these findings.
Rules: opt.nerlo-rules.nerlo-install-fetch-raw-then-run · Files: /repo/Tool/Skill_Seekers/docs/KUBERNETES_DEPLOYMENT.md, /repo/Tool/everything-claude-code/docs/zh-CN/skills/autonomous-loops/SKILL.md · reported by nerlo-install-instruction

What the review concluded

Artifact has critical vulnerabilities including remote code execution and credential exposure.

Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.

What to look at

AAK-MCP-001 · Agent/mcp/profiles/cocos-creator.mcp.json · critical · reported by agent-audit-kit
AAK-MCP-001 · Agent/mcp/profiles/unity.mcp.json · critical · reported by agent-audit-kit
AAK-LLM-SQL-RCE-001 · Tool/Skill_Seekers/src/skill_seekers/cli/adaptors/gemini.py · critical · reported by agent-audit-kit
AAK-LLM-SQL-RCE-001 · Tool/Skill_Seekers/src/skill_seekers/cli/cloud_storage_cli.py · critical · reported by agent-audit-kit
AAK-MCP-015 · Tool/Skill_Seekers/src/skill_seekers/cli/generate_router.py · critical · reported by agent-audit-kit
AAK-SECRET-003 · Tool/Skill_Seekers/src/skill_seekers/cli/storage/s3_storage.py · critical · reported by agent-audit-kit
· · critical · reported by agent-audit-kit

Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.

toolbox-governance

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

Scanners that did not run on this package (5)

nerlo-multi-source

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

Not reviewed

What the review concluded

What to look at

Install

Per-scanner reports

Scanners that examined this package (6)

agentshield

cisco-skill-scanner

agent-audit-kit

nerlo-skill-scanner (behavioral)

nerlo-skill-scanner (install-doc)

capslock

Scanners that did not run on this package (5)

nerlo-multi-source

Composite scoreOne view among many — the per-scanner reports above are primaryScan Halted

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

Not reviewed

What the review concluded

What to look at

Scan history

AI review of these findings

Why those were dismissed

In installed code — never dismissed

Upheld — the review declined to dismiss these

Not reviewed

What the review concluded

What to look at