Loading the registry…
Claude Skills are markdown + scripts loaded into Claude Code; 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.
219 critical findings reported by cisco-skill-scanner, agent-audit-kit, 21 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- base-microservice
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- base-microservice ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
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
Incomplete run
22 findings · 1.6s
v2.0.11
428 findings · 10.1s
v0.3.74
17 findings · 4.4s
v0.1.0
23 findings · 4.9s
v0.1.0
0 findings · 4.9s
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 · 1.7s
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 ·!: incompletecisco-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 490 findings across every scanner that examined this package. 198 of 219 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 17 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.
309 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: COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_command_injection_generic, DATA_EXFIL_JS_FS_ACCESS and 4 more · Files: /repo/.claude/hooks/lib/__tests__/ck-config-utils.test.cjs, /repo/.claude/hooks/lib/__tests__/statusline-integration.test.cjs, /repo/.claude/hooks/scout-block/tests/test-monorepo-scenarios.cjs and 5 more · reported by cisco-skill-scanner, nerlo-behavioral
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: AAK-AGENT-002 · Files: CLAUDE.md · reported by agent-audit-kit
1 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 · Files: /repo/.claude/hooks/lib/__tests__/SKILL.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.
64 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.claude/hooks/lib/ck-config-utils.cjs, /repo/.claude/hooks/lib/config-counter.cjs, /repo/.claude/hooks/lib/context-builder.cjs and 9 more · reported by cisco-skill-scanner
20 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.claude/hooks/lib/ck-config-utils.cjs, /repo/.claude/hooks/lib/context-builder.cjs, /repo/.claude/hooks/lib/git-info-cache.cjs and 2 more · reported by cisco-skill-scanner
19 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/.claude/SKILL.md, /repo/plans/SKILL.md and 16 more · reported by cisco-skill-scanner
19 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.claude/SKILL.md, /repo/plans/SKILL.md and 16 more · reported by cisco-skill-scanner
10 AAK-LEGAL-002
Files: libs/common/package.json, libs/database/package.json, libs/config/package.json and 7 more · reported by agent-audit-kit
17 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/cook.md, skills-missing-governance-commands/refactor.md, skills-missing-telemetry-commands/cook.md and 14 more · Files: commands/cook.md, commands/refactor.md, commands/review.md and 6 more · reported by agentshield, cisco-skill-scanner
Artifact contains critical command injection and path traversal vulnerabilities.
The artifact includes code that allows for shell command injection in multiple JavaScript files within the `.claude/hooks/` directory, potentially enabling arbitrary code execution. A critical path traversal vulnerability is also present in `usage-context-awareness.cjs`, which could lead to unauthorized file access. Additionally, there are numerous instances of file system access and dynamic execution, along with potential network egress of sensitive data.
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.
4 DATA_EXFIL_JS_NETWORK
Files: /repo/.claude/hooks/usage-context-awareness.cjs · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/.claude/hooks/lib/context-builder.cjs, /repo/.claude/hooks/lib/git-info-cache.cjs, /repo/.claude/hooks/lib/project-detector.cjs · reported by nerlo-behavioral
2 AAK-MCP-007
Files: .claude/mcp/mcp.json · reported by agent-audit-kit
2 FILE_MAGIC_MISMATCH
Files: /repo/.claude/config/adf-ignore.txt · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/.claude/hooks/.logs/hook-log.jsonl, /repo/.claudeignore · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/.claude, /repo · reported by cisco-skill-scanner
1 AAK-MCP-005
Files: .claude/mcp/mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .claude/mcp/mcp.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: .claude/hooks/usage-context-awareness.cjs · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.prettierrc.js · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md · reported by cisco-skill-scanner
1 mcp-no-desc-filesystem
Files: mcp/mcp.json · reported by agentshield
1 mcp-no-timeout-filesystem
Files: mcp/mcp.json · reported by agentshield
1 mcp-no-version-filesystem
Files: mcp/mcp.json · reported by agentshield
1 mcp-npx-y-filesystem
Files: mcp/mcp.json · reported by agentshield
1 mcp-risky-filesystem
Files: mcp/mcp.json · reported by agentshield
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/.claude/hooks/usage-context-awareness.cjs · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/.claude/hooks/usage-context-awareness.cjs · reported by nerlo-behavioral
1 permissions-no-block
Files: settings.json · reported by agentshield
Showing 25 of 92; the rest are in the per-scanner reports above.