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.
2 critical findings reported by agent-audit-kit, 0 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
github_release: https://github.com/zhangdroid/drever, 0 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- drever-workspace
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- drever-workspace ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 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
0 findings · 0.5s
v2.0.11
196 findings · 34.9s
v0.3.74
58 findings · 22.0s
v0.1.0
4 findings · 17.0s
v0.1.0
0 findings · 17.0s
v0.1.0
0 findings · 15.7s
v2.3.8
0 findings · 6.6s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.5s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Flagged85 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy ·n/a: not applicableosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 258 findings across every scanner that examined this package. 2 of 2 findings rated critical by their scanner were among the dismissals.
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.
78 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: LOW_ANALYZABILITY, FILE_MAGIC_MISMATCH, YARA_prompt_injection_unicode_steganography and 4 more · Files: /repo/examples/lab-bus-priority/design, /repo/examples/lab-seasons/design, /repo/examples/motion-recipes and 46 more · reported by cisco-skill-scanner, agent-audit-kit
64 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-TAINT-001, AAK-TAINT-003, LOW_ANALYZABILITY and 4 more · Files: e2e/storyboard.storyboard.spec.ts, e2e/studio.storyboard.spec.ts, e2e/design-import.check.spec.ts and 8 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-behavioral
2 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: AAK-AGENT-TRUST-001, MANIFEST_INVALID_NAME · Files: .github/workflows/release-smoke.yml, /repo/.github/SKILL.md · reported by agent-audit-kit, 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.
35 MANIFEST_MISSING_LICENSE
Files: /repo/packages/cli/agent-kit/skills/drever-deliver-deck/SKILL.md, /repo/packages/cli/agent-kit/skills/drever-create-deck/SKILL.md, /repo/packages/cli/agent-kit/skills/drever-author-deck/SKILL.md and 32 more · reported by cisco-skill-scanner
25 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/plugin-charts/SKILL.md, /repo/packages/vite/SKILL.md and 22 more · reported by cisco-skill-scanner
19 LOW_ANALYZABILITY
Files: /repo/packages/plugin-math, /repo/packages/compiler, /repo/packages/plugin-charts and 16 more · reported by cisco-skill-scanner
5 DATA_EXFIL_JS_NETWORK
Files: /repo/packages/cli/src/private-app.ts, /repo/scripts/release-smoke/prepare-project.mjs, /repo/scripts/release-smoke/record-release-link.mjs and 1 more · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/.agents/plugins/marketplace.json, /repo/plugins/drever/.codex-plugin/plugin.json
The model could have called any of these a false positive and did not.
15 AAK-LEGAL-002
Files: website/package.json, e2e/fixtures/core-deck/package.json, examples/spatial-stories/package.json and 12 more · reported by agent-audit-kit
Artifact may expose credentials and perform network egress.
The artifact contains code that may expose credentials and perform network egress, specifically in `/repo/scripts/release-smoke/record-release-link.mjs` and `/repo/scripts/release-smoke/verify-provenance.mjs`. Additionally, two files, `.agents/plugins/marketplace.json` and `.claude-plugin/marketplace.json`, trigger a high-severity rule related to marketplace integration. A significant portion of the installed code, across multiple packages, has low analyzability, hindering a full understanding of its behavior.
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.
2 AAK-HEALTHCARE-AI-004
Files: packages/cli/agent-kit/skills/drever-review-deck/SKILL.md, plugins/drever/skills/drever-review-deck/SKILL.md · reported by agent-audit-kit
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, .agents/plugins/marketplace.json · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/packages/cli/. · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/packages/plugin-charts/src/index.ts · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/scripts/release-smoke/record-release-link.mjs, /repo/scripts/release-smoke/verify-provenance.mjs · reported by nerlo-behavioral
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/scripts/release-smoke/prepare-project.mjs · reported by nerlo-behavioral