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.
9 critical findings reported by cisco-skill-scanner. 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 -- sourdough-pro-ai
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- sourdough-pro-ai ~/.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
23 findings · 2.5s
v2.0.11
429 findings · 34.3s
v0.3.74
9 findings · 16.6s
v0.1.0
22 findings · 29.1s
v0.1.0
0 findings · 29.1s
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 · 3.4s
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 483 findings across every scanner that examined this package. None of the 9 findings rated critical by their scanner were dismissed.
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.
14 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/docs/security/SKILL.md, /repo/docs/plans/SKILL.md, /repo/docs/superpowers/plans/SKILL.md and 4 more · reported by cisco-skill-scanner
14 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: DATA_EXFIL_JS_NETWORK, FILE_MAGIC_MISMATCH · Files: /repo/e2e/worker-api.spec.ts, /repo/e2e/dark-mode.spec.ts · 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: agents-claude-md-autorun-6420 · Files: CLAUDE.md · reported by agentshield
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.
128 HIDDEN_DATA_FILE
Files: /repo/.agents/skills/source-command-opsx-propose/SKILL.md, /repo/.agents/skills/bakery-types-workspace/iteration-1/eval-2-low-stock/without_skill/grading.json, /repo/.agents/skills/impeccable/reference/animate.md and 125 more · reported by cisco-skill-scanner
112 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/.claude/skills/impeccable/scripts/live-accept.mjs, /repo/.claude/skills/impeccable/scripts/live-inject.mjs, /repo/.claude/skills/impeccable/scripts/live-poll.mjs and 11 more · reported by cisco-skill-scanner
51 DATA_EXFIL_JS_NETWORK
Files: /repo/.claude/skills/impeccable/scripts/live-browser.js, /repo/.claude/skills/impeccable/scripts/live-poll.mjs, /repo/.claude/skills/impeccable/scripts/live-server.mjs and 8 more · reported by cisco-skill-scanner
46 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/impeccable/SKILL.md, /repo/.claude/skills/pr/SKILL.md, /repo/.claude/skills/react-doctor/SKILL.md and 43 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
1 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.env.local.example · reported by cisco-skill-scanner
Critical command injection and data exfiltration risks identified
The artifact contains critical command injection vulnerabilities in JavaScript files like `is-generated.mjs`, `live.mjs`, and `dev-worker.mjs`, allowing for shell execution. High-severity findings indicate extensive file system access and potential data exfiltration from files such as `live-accept.mjs`. Additionally, there are instances of credential access and network egress, along with hidden executable scripts and broad permission settings.
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.
19 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/.agents/skills/impeccable/scripts/live-browser.js, /repo/.agents/skills/impeccable/scripts/live-poll.mjs, /repo/.agents/skills/impeccable/scripts/live-server.mjs and 4 more · reported by nerlo-behavioral
9 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.claude/skills/impeccable/scripts/is-generated.mjs, /repo/.claude/skills/impeccable/scripts/live.mjs, /repo/.agents/skills/impeccable/scripts/is-generated.mjs and 2 more · reported by cisco-skill-scanner
6 BINARY_FILE_DETECTED
Files: /repo/.wrangler/state/v3/cache/miniflare-CacheObject/metadata.sqlite-shm, /repo/.wrangler/state/v3/kv/miniflare-KVNamespaceObject/cf84b82cd993f0a9516eba3322e1254320407c50f6778261d881400c432404df.sqlite-wal, /repo/.wrangler/state/v3/cache/miniflare-CacheObject/metadata.sqlite-wal and 3 more · reported by cisco-skill-scanner
6 UNANALYZABLE_BINARY
Files: /repo/.wrangler/state/v3/cache/miniflare-CacheObject/metadata.sqlite-shm, /repo/.wrangler/state/v3/kv/miniflare-KVNamespaceObject/cf84b82cd993f0a9516eba3322e1254320407c50f6778261d881400c432404df.sqlite-wal, /repo/.wrangler/state/v3/cache/miniflare-CacheObject/metadata.sqlite-wal and 3 more · reported by cisco-skill-scanner
5 FILE_MAGIC_MISMATCH
Files: /repo/.claude/skills/ui-ux-pro-max/data/react-performance.csv, /repo/.agents/skills/ui-ux-pro-max/data/react-performance.csv, /repo/DESIGN.md · reported by cisco-skill-scanner
5 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/skills/ui-ux-pro-max/scripts/search.py, /repo/.agents/skills/impeccable/scripts/live-browser.js, /repo/.agents/skills/impeccable/scripts/modern-screenshot.umd.js and 2 more · reported by cisco-skill-scanner
4 PYCACHE_FILES_DETECTED
Files: /repo/.claude/skills/ui-ux-pro-max/scripts/__pycache__, /repo/.agents/skills/ui-ux-pro-max/scripts/__pycache__ · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/.claude/skills/impeccable, /repo/.agents/skills/impeccable, /repo · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/worker.ts · reported by nerlo-behavioral
2 AAK-HEALTHCARE-AI-004
Files: .claude/skills/impeccable/reference/critique.md, .agents/skills/impeccable/reference/critique.md · reported by agent-audit-kit
2 AAK-MCP-014
Files: .claude/skills/impeccable/scripts/live-server.mjs, .agents/skills/impeccable/scripts/live-server.mjs · reported by agent-audit-kit
2 hooks-bg-process-1080
Files: hooks/ui-review-on-stop.sh, .claude/hooks/ui-review-on-stop.sh · reported by agentshield
2 hooks-chained-commands-0
Files: settings.json, .claude/settings.json · reported by agentshield
2 hooks-chained-commands-1
Files: settings.json, .claude/settings.json · reported by agentshield
2 hooks-chained-commands-2
Files: settings.json, .claude/settings.json · reported by agentshield
2 hooks-silent-fail-21
Files: settings.json, .claude/settings.json · reported by agentshield
2 MANIFEST_INVALID_NAME
Files: /repo/.cursor/commands/SKILL.md, /repo/.claude/commands/opsx/SKILL.md · reported by cisco-skill-scanner
2 permissions-no-deny-list
Files: settings.json, .claude/settings.json · reported by agentshield
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-SECRET-006
Files: .env.local.example · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.json · reported by agent-audit-kit
1 agents-bash-access-.claude/agents/bakery-math-reviewer.md
Files: .claude/agents/bakery-math-reviewer.md · reported by agentshield
1 agents-bash-access-.claude/agents/storage-sync-reviewer.md
Files: .claude/agents/storage-sync-reviewer.md · reported by agentshield
1 agents-bash-access-.claude/agents/worker-security-reviewer.md
Files: .claude/agents/worker-security-reviewer.md · reported by agentshield
1 agents-bash-access-agents/bakery-math-reviewer.md
Files: agents/bakery-math-reviewer.md · reported by agentshield
1 agents-bash-access-agents/storage-sync-reviewer.md
Files: agents/storage-sync-reviewer.md · reported by agentshield
1 agents-bash-access-agents/worker-security-reviewer.md
Files: agents/worker-security-reviewer.md · reported by agentshield
1 agents-no-model-.claude/agents/ui-reviewer.md
Files: .claude/agents/ui-reviewer.md · reported by agentshield
1 agents-no-model-agents/ui-reviewer.md
Files: agents/ui-reviewer.md · reported by agentshield
1 agents-no-tools-.claude/agents/ui-reviewer.md
Files: .claude/agents/ui-reviewer.md · reported by agentshield
1 agents-no-tools-agents/ui-reviewer.md
Files: agents/ui-reviewer.md · reported by agentshield
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
Showing 25 of 154; the rest are in the per-scanner reports above.