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.
2 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 -- chat-by-mason-james
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- chat-by-mason-james ~/.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
19 findings · 1.1s
v2.0.11
97 findings · 15.3s
v0.3.74
22 findings · 22.5s
v0.1.0
5 findings · 7.9s
v0.1.0
1 finding · 8.0s
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 · 0.9s
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 144 findings across every scanner that examined this package. None of the 2 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 12 findings 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.
32 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_unicode_steganography, OVERSIZED_FILE, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: /repo/apps/docs/images/ai-models.gif, /repo/apps/docs/images/canvas.gif, /repo/apps/docs/images/web-search.gif and 2 more · reported by cisco-skill-scanner, nerlo-install-instruction
14 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-GHA-IMMUTABLE-001, permissions-no-block, hooks-no-pretooluse · Files: .github/workflows/build-push-ghcr.yml, .github/workflows/lint.yml, .github/workflows/zizmor.yml and 6 more · reported by agent-audit-kit, agentshield
6 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-AGENT-002, secrets-claude-md-env-5107, MANIFEST_MISSING_LICENSE and 1 more · Files: AGENTS.md, CLAUDE.md, /repo/apps/docs/.claude/skills/review-docs/SKILL.md and 2 more · reported by agent-audit-kit, agentshield, 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.
18 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/general/SKILL.md, /repo/apps/chat/.claude/skills/ultracite/SKILL.md, /repo/apps/chat/.claude/skills/chat-context/SKILL.md and 15 more · reported by cisco-skill-scanner
17 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/chat/components/ai-elements/prompt-input.tsx, /repo/apps/chat/components/attachment-list.tsx, /repo/apps/chat/components/email-auth-form.tsx and 12 more · reported by cisco-skill-scanner
10 HIDDEN_DATA_FILE
Files: /repo/.beads/beads.base.meta.json, /repo/.beads/beads.left.meta.json, /repo/.beads/beads.base.jsonl and 7 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/apps/chat/.claude/skills/ultracite/SKILL.md, /repo/apps/chat/.cursor/skills/ultracite/SKILL.md, /repo/SKILL.md and 7 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/chat/lib/ai/gateways/openai-compatible-gateway.ts, /repo/apps/chat/lib/ai/gateways/openai-gateway.ts, /repo/apps/chat/lib/ai/gateways/openrouter-gateway.ts and 1 more
The model could have called any of these a false positive and did not.
1 AAK-LEGAL-002
Files: apps/docs/package.json · reported by agent-audit-kit
12 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-.claude/commands/rp-build.md, skills-missing-governance-commands/rp-investigate.md, skills-missing-governance-.claude/commands/rp-investigate.md and 9 more · Files: .claude/commands/rp-build.md, commands/rp-investigate.md, .claude/commands/rp-investigate.md and 3 more · reported by agentshield
Critical command injection and high-risk data exfiltration capabilities.
The artifact contains critical command injection vulnerabilities, including `eval` usage in `code-execution.ts` and coercive injection in `deep-research.ts`. It also exhibits high-risk capabilities such as secret exfiltration to network egress in multiple AI gateway files and file system access in `docker-migrate.cjs`. Additionally, there are findings related to credential access and OAuth handling in `chat/api/chat/route.ts` and `mcp-connect-dialog.tsx`.
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.
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/apps/chat/scripts/docker-migrate.cjs · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo, /repo/packages/cli · reported by cisco-skill-scanner
1 AAK-MCP-005
Files: .cursor/mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .cursor/mcp.json · reported by agent-audit-kit
1 AAK-MCP-BETTERAUTH-CVE-2026-53512-001
Files: package-lock.json · reported by agent-audit-kit
1 AAK-OAUTH-001
Files: apps/chat/components/settings/mcp-connect-dialog.tsx · reported by agent-audit-kit
1 AAK-OAUTH-007
Files: apps/chat/components/settings/mcp-connect-dialog.tsx · reported by agent-audit-kit
1 AAK-SECRET-004
Files: apps/chat/app/(chat)/api/chat/route.ts · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/apps/chat/lib/ai/tools/code-execution.ts · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/apps/chat/lib/ai/prompts.ts · reported by cisco-skill-scanner
1 hooks-no-pretooluse
Files: .cursor/settings.json · reported by agentshield
1 mcp-no-desc-next-devtools
Files: .cursor/mcp.json · reported by agentshield
1 mcp-npx-y-next-devtools
Files: .cursor/mcp.json · reported by agentshield
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/apps/chat/lib/ai/gateways/openai-gateway.ts · reported by nerlo-behavioral
1 permissions-no-block
Files: .cursor/settings.json · reported by agentshield
1 YARA_coercive_injection_generic
Files: /repo/apps/chat/lib/ai/tools/deep-research/deep-research.ts · reported by cisco-skill-scanner