Loading the registry…
Examine similar files for consistency violations. Compares 2+ files that should follow the same pattern, decomposes comparison areas, and produces a work items list of differences. Use when user says 'hobgoblin', 'consistency check', or 'compare patterns'.
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.
14 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 -- 'robmadole/agent-tools (hobgoblin)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'robmadole/agent-tools (hobgoblin)' ~/.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
97 findings · 16.8s
v0.3.74
10 findings · 4.5s
v0.1.0
3 findings · 5.9s
v0.1.0
2 findings · 5.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.3s
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 · 1.0s
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 21, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 112 findings across every scanner that examined this package. None of the 14 findings rated critical by their scanner were dismissed.
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.
7 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/plugins/testing/skills/browser-test/references/SKILL.md, /repo/plugins/testing/skills/jit-catch/references/SKILL.md, /repo/plugins/testing/skills/browser-test/SKILL.md and 2 more · reported by cisco-skill-scanner
6 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-MCP-005, AAK-MCP-ATTEST-001 · Files: plugins/testing/.mcp.json · reported by agent-audit-kit
4 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, TOOL_ABUSE_UNDECLARED_NETWORK, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: CLAUDE.md, /repo/repo/CLAUDE.md, /repo/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
3 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_FS_ACCESS, LOW_ANALYZABILITY · Files: /repo/plugins/testing/skills/browser-test/scripts/validate.js, /repo/plugins/testing/skills/browser-test · 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.
62 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/quality/skills/deskcheck/scripts/fixture.py, /repo/plugins/quality/skills/deskcheck/scripts/selftest.py, /repo/plugins/quality/skills/deskcheck/scripts/server.py · reported by cisco-skill-scanner
10 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/plugins/quality/skills/deskcheck/assets/mermaid.min.js · reported by cisco-skill-scanner
4 COMMAND_INJECTION_OS_SYSTEM
Files: /repo/plugins/quality/skills/deskcheck/scripts/server.py, /repo/plugins/quality/skills/deskcheck/scripts/fetch_comments.py · reported by cisco-skill-scanner
4 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/plugins/quality/skills/deskcheck/scripts/fetch_comments.py, /repo/plugins/quality/skills/deskcheck/scripts/server.py · reported by cisco-skill-scanner
3 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
Critical command injection and potential secret exfiltration identified.
The artifact contains multiple critical command injection vulnerabilities, specifically via JavaScript function constructors in `mermaid.min.js` and OS system calls in Python scripts like `fetch_comments.py` and `server.py`. It also exhibits high-severity findings related to potential secret exfiltration to external networks from `fixture.py` and `server.py`. Additionally, resource abuse via infinite loops is present in `fetch_comments.py` and `server.py`, alongside numerous network egress findings.
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 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/quality/skills/deskcheck/SKILL.md, /repo/plugins/develop/skills/hobgoblin/SKILL.md, /repo/SKILL.md · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/plugins/quality/skills/deskcheck/scripts/fixture.py, /repo/plugins/quality/skills/deskcheck/scripts/server.py · reported by nerlo-behavioral
1 LOW_ANALYZABILITY
Files: /repo/plugins/quality/skills/deskcheck · reported by cisco-skill-scanner
1 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/plugins/quality/skills/deskcheck/repo/plugins/quality/skills/deskcheck/SKILL.md · reported by cisco-skill-scanner