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.
15 critical findings reported by agent-audit-kit, 5 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 -- @storybook/root
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- @storybook/root ~/.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
7 findings · 0.9s
v2.0.11
Timed out
0 findings · 300.0s
v0.3.74
150 findings · 296.4s
v0.1.0
17 findings · 99.6s
v0.1.0
2 findings · 100.0s
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 · 0.8s
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 ·!: timeoutagent-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 176 findings across every scanner that examined this package. 10 of 15 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.
39 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-SSRF-001, AAK-TAINT-003 and 9 more · Files: agent-eval/lib/mcp/codex-browser-mock.test.ts, agent-eval/lib/mcp/preview-browser-mock.test.ts, code/lib/mcp/src/tools/outcome-unwrap.test.ts and 11 more · reported by agent-audit-kit, nerlo-behavioral
9 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-002, AAK-AGENT-TRUST-001, AAK-LEGAL-002 and 2 more · Files: .github/workflows/claude.yml, .github/workflows/claude-code-review.yml, .github/scripts/package.json and 5 more · reported by agent-audit-kit, agentshield
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: AAK-MCP-005, AAK-MCP-ATTEST-001 · Files: .github/copilot-mcp.json · reported by 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: opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/docs/get-started/frameworks/angular-vite.mdx · reported by nerlo-install-instruction
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.
66 AAK-LEGAL-002
Files: package.json, scripts/package.json, code/package.json and 63 more · reported by agent-audit-kit
10 AAK-SECRET-004
Files: scripts/upload-bench.ts, scripts/tasks/chromatic.ts, scripts/bench/bench-packages.ts and 3 more · reported by agent-audit-kit
9 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/agent-eval/lib/mcp/start-storybook-mcp.mjs, /repo/code/addons/mcp/src/auth/composition-auth.ts, /repo/code/core/src/manager-api/modules/refs.ts and 3 more · reported by nerlo-behavioral
5 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/code/core/src/core-server/utils/whats-new.ts, /repo/scripts/bench/bench-packages.ts, /repo/scripts/release/utils/get-github-info.ts and 2 more · reported by nerlo-behavioral
4 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, code/lib/codex-plugin/.agents/plugins/marketplace.json, code/lib/claude-plugin/.claude-plugin/marketplace.json and 1 more
Artifact contains critical vulnerabilities, including SSRF and exposed secrets.
The artifact exhibits critical Server-Side Request Forgery (SSRF) vulnerabilities in `code/addons/mcp/src/tools/tool-registry.ts` and `code/lib/mcp/src/tools/register.ts`, allowing network egress and potential access to internal resources. It also has critical taint vulnerabilities in `scripts/run-registry.ts` that could lead to code execution. Additionally, multiple high-severity findings indicate exposed secrets in files like `code/core/src/manager/components/review/constants.ts` and `scripts/bench/bench-packages.ts`, which could facilitate credential access and further network egress.
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.
3 AAK-MCP-ATTEST-001
Files: .cursor/mcp.json, test-storybooks/mcp/.mcp.json · reported by agent-audit-kit
2 AAK-MCP-001
Files: .cursor/mcp.json, test-storybooks/mcp/.mcp.json · reported by agent-audit-kit
2 AAK-MCP-009
Files: .cursor/mcp.json, test-storybooks/mcp/.mcp.json · reported by agent-audit-kit
2 AAK-MCP-018
Files: code/lib/mcp/bin.ts, code/addons/mcp/src/mcp-handler.ts · reported by agent-audit-kit
2 AAK-SSRF-001
Files: code/lib/mcp/src/tools/register.ts, code/addons/mcp/src/tools/tool-registry.ts · reported by agent-audit-kit
2 AAK-SSRF-005
Files: code/lib/mcp/src/tools/register.ts, code/addons/mcp/src/tools/tool-registry.ts · reported by agent-audit-kit
1 AAK-MCP-APPS-001
Files: code/addons/mcp/src/tools/preview-stories/preview-stories-app-template.html · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: scripts/event-log-collector.ts · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: code/addons/mcp/src/auth/composition-auth.ts · reported by agent-audit-kit
1 AAK-OAUTH-005
Files: code/addons/mcp/src/auth/composition-auth.ts · reported by agent-audit-kit
1 AAK-OAUTH-007
Files: code/addons/mcp/src/auth/composition-auth.ts · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: code/addons/mcp/src/mcp-handler.ts · reported by agent-audit-kit
1 AAK-SKILL-002
Files: .agents/skills/minor-release/SKILL.md · reported by agent-audit-kit
1 AAK-SKILL-004
Files: .agents/skills/pr/SKILL.md · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 AAK-TAINT-001
Files: scripts/run-registry.ts · reported by agent-audit-kit
1 AAK-TAINT-003
Files: scripts/event-log-collector.ts · reported by agent-audit-kit
1 hooks-no-pretooluse
Files: test-storybooks/mcp/.claude/settings.local.json · reported by agentshield
1 mcp-env-inherit-wallaby
Files: .cursor/mcp.json · reported by agentshield
1 mcp-no-desc-storybook-ui
Files: .cursor/mcp.json · reported by agentshield
1 mcp-no-desc-wallaby
Files: .cursor/mcp.json · reported by agentshield
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/scripts/build-package.ts · reported by nerlo-behavioral
1 permissions-no-deny-list
Files: test-storybooks/mcp/.claude/settings.local.json · reported by agentshield
Showing 25 of 39; the rest are in the per-scanner reports above.