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.
Claude Skills install to a single target, no runtime picker.
nerlo install -- @tidy/source
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- @tidy/source ~/.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
10 findings · 1.1s
v2.0.11
3985 findings · 297.2s
v0.3.74
116 findings · 138.9s
v0.1.0
24 findings · 51.2s
v0.1.0
16 findings · 51.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
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: 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 4,151 findings across every scanner that examined this package.
Not reviewed is not the same as clean. Those 1 finding 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.
193 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, agents-comment-injection-0, AAK-HEALTHCARE-AI-004 and 5 more · Files: .github/skills/bmad-tea/resources/knowledge/ci-burn-in.md, .github/skills/bmad-tea/resources/knowledge/nfr-criteria.md, CLAUDE.md and 141 more · reported by agent-audit-kit, agentshield, cisco-skill-scanner
36 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FILE_MAGIC_MISMATCH, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/.github/skills/bmad-market-research/research.template.md, /repo/.github/skills/bmad-technical-research/research.template.md, /repo/.github/skills/bmad-domain-research/research.template.md and 12 more · reported by cisco-skill-scanner, nerlo-install-instruction
30 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: HIDDEN_EXECUTABLE_SCRIPT, DATA_EXFIL_JS_NETWORK, SECRET_PASSWORD_VAR · Files: /repo/.qwen/skills/bmad-workflow-builder/scripts/tests/test_generate_convert_report.py, /repo/.agent/skills/bmad-init/scripts/tests/test_bmad_init.py, /repo/.qwen/skills/bmad-init/scripts/tests/test_bmad_init.py and 24 more · reported by cisco-skill-scanner
1 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: LOW_ANALYZABILITY · Files: /repo/.github/skills/monitor-ci · 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.
2,217 HIDDEN_DATA_FILE
Files: /repo/.gemini/skills/bmad-testarch-atdd/steps-c/step-02-generation-mode.md, /repo/.qwen/skills/bmad-tea/resources/knowledge/playwright-cli.md, /repo/.qwen/skills/bmad-agent-builder/quality-scan-structure.md and 2214 more · reported by cisco-skill-scanner
872 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/bmad-testarch-automate/SKILL.md, /repo/.claude/skills/bmad-qa-generate-e2e-tests/SKILL.md, /repo/.claude/skills/bmad-create-prd/SKILL.md and 869 more · reported by cisco-skill-scanner
243 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.claude/skills/bmad-create-prd/data/SKILL.md, /repo/.claude/skills/bmad-create-prd/steps-c/SKILL.md and 240 more · reported by cisco-skill-scanner
242 FILE_MAGIC_MISMATCH
Files: /repo/.claude/skills/bmad-market-research/research.template.md, /repo/.claude/skills/bmad-technical-research/research.template.md, /repo/.claude/skills/bmad-domain-research/research.template.md and 90 more · reported by cisco-skill-scanner
104 HIDDEN_EXECUTABLE_SCRIPT
The model could have called any of these a false positive and did not.
3 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/.github/skills/bmad-agent-builder/scripts/generate-html-report.py, /repo/.github/skills/bmad-workflow-builder/scripts/generate-convert-report.py, /repo/.github/skills/bmad-workflow-builder/scripts/generate-html-report.py · reported by nerlo-behavioral
1 The model did not answer for these findings.
Rules: MANIFEST_INVALID_NAME · Files: /repo/.github/skills/bmad-agent-builder/assets/SKILL.md · reported by cisco-skill-scanner
Artifact contains executable scripts and permissive shell execution capabilities.
The artifact includes numerous hidden executable scripts, particularly Python scripts within agent skills directories, which can perform shell execution. It also contains code capable of dynamic execution within Python. Furthermore, the artifact's settings grant permissive Bash execution for Python scripts and lack a deny-list for permissions, increasing the potential for broad system interaction. Several files contain content identified as a 'wild corpus', which may warrant further review.
Concern level assessed by the review: High. 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.
50 AAK-HEALTHCARE-AI-004
Files: .claude/skills/bmad-agent-builder/quality-scan-prompt-craft.md, .claude/skills/bmad-workflow-builder/quality-scan-prompt-craft.md, .claude/skills/bmad-agent-tech-writer/SKILL.md and 47 more · reported by agent-audit-kit
38 YARA_autonomy_abuse_generic
Files: /repo/.claude/skills/bmad-validate-prd/steps-v/SKILL.md, /repo/.claude/skills/bmad-edit-prd/steps-e/SKILL.md, /repo/.gemini/skills/bmad-validate-prd/steps-v/SKILL.md and 12 more · reported by cisco-skill-scanner
33 AAK-AGENT-TRUST-004
Files: .gemini/skills/bmad-testarch-atdd/atdd-checklist-template.md, .gemini/skills/bmad-testarch-test-design/test-design-qa-template.md, .gemini/skills/bmad-agent-builder/build-process.md and 30 more · reported by agent-audit-kit
21 MANIFEST_INVALID_NAME
Files: /repo/.claude/skills/bmad-workflow-builder/assets/SKILL.md, /repo/.gemini/skills/bmad-workflow-builder/assets/SKILL.md, /repo/.qwen/skills/bmad-workflow-builder/assets/SKILL.md and 18 more · reported by cisco-skill-scanner
21 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/.agent/skills/bmad-agent-builder/scripts/generate-html-report.py, /repo/.agent/skills/bmad-workflow-builder/scripts/generate-convert-report.py, /repo/.agent/skills/bmad-workflow-builder/scripts/generate-html-report.py and 18 more · reported by nerlo-behavioral
14 AAK-IPI-WILD-CORPUS-001
Files: .claude/skills/bmad-tea/resources/knowledge/ci-burn-in.md, .claude/skills/bmad-tea/resources/knowledge/nfr-criteria.md, .gemini/skills/bmad-tea/resources/knowledge/ci-burn-in.md and 11 more · reported by agent-audit-kit
14 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.agent/skills/bmad-tea/resources/knowledge/ci-burn-in.md, /repo/.agent/skills/bmad-tea/resources/knowledge/contract-testing.md, /repo/.claude/skills/bmad-tea/resources/knowledge/ci-burn-in.md and 11 more · reported by nerlo-install-instruction
4 hooks-no-pretooluse
Files: settings.json, .claude/settings.json, .gemini/settings.json and 1 more · reported by agentshield
3 permissions-no-block
Files: settings.json, .claude/settings.json, .gemini/settings.json · reported by agentshield
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/_bmad/tea/workflows/testarch/. · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/.opencode/skills/monitor-ci, /repo/.agents/skills/monitor-ci · reported by cisco-skill-scanner
1 AAK-MCP-005
Files: .gemini/settings.json · reported by agent-audit-kit
1 AAK-MCP-007
Files: .gemini/settings.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .gemini/settings.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/web/src/store/authSlice.ts · reported by cisco-skill-scanner
1 permissions-no-deny-list
Files: .qwen/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 *)
Files: .qwen/settings.json · reported by agentshield
Showing 25 of 146; the rest are in the per-scanner reports above.