Loading the registry…
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
71 critical findings reported by cisco-skill-scanner, agent-audit-kit, 61 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- huuanh20/awesome-ai-agent-skills
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
14 findings · 0.6s
v2.0.11
662 findings · 36.4s
v0.3.74
15 findings · 21.9s
v0.1.0
0 findings · 8.4s
v0.1.0
5 findings · 8.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.8s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 22, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
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.
Out of 696 findings across every scanner that examined this package. None of the 71 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 2 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
6 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE, MANIFEST_INVALID_NAME · Files: /repo/.github/SKILL.md, /repo/.github/ISSUE_TEMPLATE/SKILL.md · reported by cisco-skill-scanner
1 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: HIDDEN_DATA_FILE · Files: /repo/.agents/agents.md · reported by cisco-skill-scanner
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.
262 MANIFEST_MISSING_LICENSE
Files: /repo/.codex/skills/problem-solving/SKILL.md, /repo/.codex/skills/ck-plan/SKILL.md, /repo/.codex/skills/srs-generator/SKILL.md and 259 more · reported by cisco-skill-scanner
92 HIDDEN_DATA_FILE
Files: /repo/.agents/rules/code-quality.md, /repo/.agents/hooks.json, /repo/.agents/workflows/srs.md and 89 more · reported by cisco-skill-scanner
75 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.codex/skills/ck-plan/SKILL.md, /repo/.codex/skills/ck-fix/SKILL.md, /repo/.codex/skills/ck-brainstorm/SKILL.md and 72 more · reported by cisco-skill-scanner
74 MANIFEST_INVALID_NAME
Files: /repo/.codex/skills/problem-solving/collision-zone-thinking/SKILL.md, /repo/.claude/skills/problem-solving/collision-zone-thinking/SKILL.md, /repo/development-skills/skills/problem-solving/collision-zone-thinking/SKILL.md and 71 more · reported by cisco-skill-scanner
47 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.codex/skills/playwright-skill/run.js, /repo/.claude/skills/playwright-skill/run.js, /repo/development-skills/skills/playwright-skill/run.js and 5 more
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.agents/skills/sequential-thinking/references/examples.md, /repo/.agents/skills/mermaidjs-v11/references/examples.md · reported by cisco-skill-scanner
Critical command injection and path traversal vulnerabilities detected.
The artifact contains critical command injection vulnerabilities via JavaScript `child_process` and `eval` calls, notably in `playwright-skill/run.js` and `playwright-skill/lib/helpers.js`, allowing for arbitrary shell execution. Path traversal vulnerabilities in `session_init.py` could lead to unauthorized file access. Additionally, the artifact has capabilities for file system access and network egress, as indicated by data exfiltration findings. Several hidden executable scripts are also present.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
38 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.codex/skills/playwright-skill/run.js, /repo/.claude/skills/playwright-skill/run.js, /repo/development-skills/skills/playwright-skill/run.js and 3 more · reported by cisco-skill-scanner
22 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/scripts/strict_gate.py, /repo/.agents/skills/skill-creator/scripts/package_skill.py, /repo/.agents/scripts/session_init.py and 19 more · reported by cisco-skill-scanner
12 COMMAND_INJECTION_EVAL
Files: /repo/.codex/skills/playwright-skill/lib/helpers.js, /repo/.claude/skills/playwright-skill/lib/helpers.js, /repo/development-skills/skills/playwright-skill/lib/helpers.js and 2 more · reported by cisco-skill-scanner
12 DATA_EXFIL_JS_NETWORK
Files: /repo/.codex/skills/playwright-skill/lib/helpers.js, /repo/.claude/skills/playwright-skill/lib/helpers.js, /repo/development-skills/skills/playwright-skill/lib/helpers.js and 2 more · reported by cisco-skill-scanner
5 AAK-IPI-WILD-CORPUS-001
Files: .codex/skills/srs-generator/references/gap-detection-guide.md, .claude/skills/srs-generator/references/gap-detection-guide.md, srs-skills/skills/srs-generator/references/gap-detection-guide.md and 2 more · reported by agent-audit-kit
5 AAK-SKILL-001
Files: .codex/skills/mermaidjs-v11/SKILL.md, .claude/skills/mermaidjs-v11/SKILL.md, development-skills/skills/mermaidjs-v11/SKILL.md and 2 more · reported by agent-audit-kit
5 AAK-SKILL-003
Files: .codex/skills/team-fe/SKILL.md, .claude/skills/team-fe/SKILL.md, .cursor/skills/team-fe/SKILL.md and 2 more · reported by agent-audit-kit
5 FIND_EXEC_PATTERN
Files: /repo/.codex/skills/mermaidjs-v11/references/SKILL.md, /repo/.claude/skills/mermaidjs-v11/references/SKILL.md, /repo/development-skills/skills/mermaidjs-v11/references/SKILL.md and 2 more · reported by cisco-skill-scanner
5 LOW_ANALYZABILITY
Files: /repo/.claude/skills/playwright-skill, /repo/development-skills/skills/playwright-skill, /repo/.agents/skills/playwright-skill and 2 more · reported by cisco-skill-scanner
5 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/.agents/skills/mermaidjs-v11/references/cli-usage.md, /repo/.claude/skills/mermaidjs-v11/references/cli-usage.md, /repo/.codex/skills/mermaidjs-v11/references/cli-usage.md and 2 more · reported by nerlo-install-instruction
4 FILE_MAGIC_MISMATCH
Files: /repo/.codex/skills/ck-plan-json/agents/openai.yaml, /repo/.cursor/skills/ck-plan-json/agents/openai.yaml · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/.agents/., /repo/development-skills/., /repo/. · reported by cisco-skill-scanner
2 PATH_TRAVERSAL_OPEN
Files: /repo/.agents/scripts/session_init.py · reported by cisco-skill-scanner
1 agents-bash-access-agents/code-reviewer.md
Files: agents/code-reviewer.md · reported by agentshield
1 agents-bash-access-agents/debugger.md
Files: agents/debugger.md · reported by agentshield
1 agents-bash-access-agents/git-manager.md
Files: agents/git-manager.md · reported by agentshield
1 agents-bash-access-agents/playwright-capture.md
Files: agents/playwright-capture.md · reported by agentshield
1 agents-bash-access-agents/quality-reviewer.md
Files: agents/quality-reviewer.md · reported by agentshield
1 agents-bash-access-agents/scout.md
Files: agents/scout.md · reported by agentshield
1 agents-bash-access-agents/tester.md
Files: agents/tester.md · reported by agentshield
1 agents-escalation-chain-agents/debugger.md
Files: agents/debugger.md · reported by agentshield
1 agents-escalation-chain-agents/tester.md
Files: agents/tester.md · reported by agentshield
1 agents-expensive-readonly-agents/plan-reviewer.md
Files: agents/plan-reviewer.md · reported by agentshield
1 hooks-code-transcript-access-22
Files: hooks/session_end.py · reported by agentshield
1 hooks-code-transcript-access-252
Files: hooks/session_state.py · reported by agentshield
1 permissions-negated-2230
Files: agents/git-manager.md · reported by agentshield
1 permissions-no-block
Files: settings.json · reported by agentshield
Showing 25 of 144; the rest are in the per-scanner reports above.