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.
12 critical findings reported by cisco-skill-scanner, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/ingtian/witness, 56 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- witness
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- witness ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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.
v2.0.11
50 findings · 8.2s
v0.3.74
5 findings · 3.7s
v0.2.0
0 findings · 5.2s
v0.2.0
1 finding · 5.3s
vv0.3.2
Incomplete run
0 findings · 2.8s
v0.1.0
0 findings · 15.0s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
4 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 24, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source: complete | rejected |
| Aug 2, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 28, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | 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 56 findings across every scanner that examined this package. 10 of 12 findings rated critical by their scanner were among the dismissals.
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.
20 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_prompt_injection_generic, DATA_EXFIL_JS_FS_ACCESS and 1 more · Files: /repo/npm/opencode/bin/witness.test.js, /repo/internal/platform/fence_case_test.go, /repo/npm/opencode/bin/platform.test.js · reported by cisco-skill-scanner
2 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: FILE_MAGIC_MISMATCH, AAK-AGENT-001 · Files: /repo/CLAUDE.md, AGENTS.md · reported by cisco-skill-scanner, agent-audit-kit
2 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 · Files: /repo/prompts/lens/example/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.
10 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/prompts/SKILL.md, /repo/prompts/default/SKILL.md and 7 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/prompts/SKILL.md, /repo/prompts/default/SKILL.md and 7 more · reported by cisco-skill-scanner
3 FILE_MAGIC_MISMATCH
Files: /repo/npm/opencode/bin/model.js, /repo/llms.txt · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/npm/opencode/bin/witness.js · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: prompts/default/extract.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
1 The model did not answer for these findings.
Rules: AAK-AGENT-TRUST-001 · Files: .github/workflows/npm-publish.yml · reported by agent-audit-kit
Critical command injection risk via child process execution.
The artifact contains critical command injection vulnerabilities in `/repo/npm/opencode/bin/witness.js`, allowing for shell execution. A high-severity finding indicates a potential credential exposure in `npm/opencode/bin/model.js`. Additionally, the artifact exhibits low analyzability in `/repo/npm/opencode`, which may obscure further risks.
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.
1 AAK-SECRET-004
Files: npm/opencode/bin/model.js · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/npm/opencode · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/install.sh · reported by nerlo-install-instruction