Loading the registry…
Audit ChatGPT and Codex plugin or skill repositories, validate marketplace and manifest structure, inventory local installations, and prepare safe plugin installation plans. Use when working with marketplace.json, .codex-plugin/plugin.json, SKILL.md catalogs, plugin compatibility reports, or explicit marketplace installation requests; default to dry-run and do not modify installed plugins unless the user explicitly requests application.
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.
6 critical findings reported by agent-audit-kit. 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 -- 'tdouguo/build-plugins (manage-codex-build-marketplace)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'tdouguo/build-plugins (manage-codex-build-marketplace)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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
Timed out
0 findings · 300.0s
v0.3.74
356 findings · 311.4s
v0.1.0
44 findings · 127.7s
v0.1.0
34 findings · 127.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.3s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.2s
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 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 434 findings across every scanner that examined this package. None of the 6 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 417 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
The model could have called any of these a false positive and did not.
5 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/plugins/skill-office-quotes/skills/office-quotes/scripts/office-quotes.js, /repo/plugins/skill-tavily/skills/tavily/scripts/extract.mjs, /repo/plugins/skill-tavily/skills/tavily/scripts/search.mjs and 2 more · reported by nerlo-behavioral
4 AAK-LEGAL-002
Files: plugins/skill-develop-web-game/skills/develop-web-game/package.json, plugins/skill-wechat-toolkit/skills/wechat-toolkit/package.json, plugins/skill-wechat-toolkit/skills/wechat-toolkit/scripts/downloader/package.json and 1 more · reported by agent-audit-kit
3 AAK-OAUTH-007
Files: plugins/skill-nest-devices/skills/nest-devices/scripts/nest-webhook.py, plugins/skill-nest-devices/skills/nest-devices/scripts/nest.py, plugins/skill-security-ownership-map/skills/security-ownership-map/scripts/build_ownership_map.py · reported by agent-audit-kit
1 AAK-MCP-018
Files: plugins/skill-chatgpt-apps/skills/chatgpt-apps/scripts/scaffold_node_ext_apps.mjs · reported by agent-audit-kit
1 AAK-MCP-HTTP-NOAUTH-SERVER-001
Files: plugins/skill-chatgpt-apps/skills/chatgpt-apps/scripts/scaffold_node_ext_apps.mjs · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: plugins/skill-clawguardian/skills/clawguardian/billing/billing_endpoints.py · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: plugins/skill-wechat-toolkit/skills/wechat-toolkit/scripts/publisher/publish_with_video.js · reported by agent-audit-kit
1 AAK-TASKS-003
Files: plugins/skill-webgl-data-peeler/skills/webgl-data-peeler/scripts/_vendor/UnityPy/classes/generated.py · reported by agent-audit-kit
386 The review call did not complete.
Rules: AAK-SKILL-001, AAK-INDIA-PII-001, AAK-SECRET-003 and 11 more · Files: plugins/skill-office-quotes/skills/office-quotes/SKILL.md, plugins/skill-playwright-mcp/skills/playwright-mcp/SKILL.md, plugins/skill-api-gateway/skills/api-gateway/references/tally/README.md and 76 more · reported by agent-audit-kit, nerlo-behavioral, nerlo-install-instruction
31 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: opt.nerlo-rules.nerlo-install-reverse-shell-directive, opt.nerlo-rules.nerlo-install-fetch-raw-then-run, AAK-HEALTHCARE-AI-004 and 2 more · Files: /repo/plugins/skill-clawguardian/skills/clawguardian/definitions/tool-abuse.json, /repo/plugins/skill-xurl/skills/xurl/references/setup-and-auth.md, catalog/imported-assets.json and 21 more · reported by nerlo-install-instruction, agent-audit-kit
Exposes secrets and PII; potential network egress and shell execution.
The artifact contains critical findings for exposing secrets and personally identifiable information (PII) within its installed code. These include secrets found in various scripts and PII in reference files. High severity findings also indicate potential network egress of secrets and shell execution during installation, which warrant careful review.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 6 of 6; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.