Loading the registry…
Cross-platform installer for Heart of Gold skills — works with Codex, OpenCode, Pi, Claude Code, and more
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.
31 critical findings reported by cisco-skill-scanner, agent-audit-kit, 25 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/ondrej-svec/heart-of-gold-toolkit, 330 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- @heart-of-gold/toolkit
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- @heart-of-gold/toolkit ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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
0 findings · 0.5s
v2.0.11
148 findings · 15.4s
v0.3.74
20 findings · 7.2s
v0.1.0
1 finding · 4.1s
v0.1.0
21 findings · 4.1s
v0.1.0
0 findings · 9.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | 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 190 findings across every scanner that examined this package. None of the 31 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 144 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.
27 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, opt.nerlo-rules.nerlo-install-run-bundled-artifact, MANIFEST_MISSING_LICENSE · Files: /repo/plugins/marvin/skills/share-server-control/docs/SKILL.md, /repo/plugins/marvin/skills/share-html/docs/SKILL.md, /repo/plugins/marvin/skills/share-server-setup/docs/SKILL.md and 10 more · reported by cisco-skill-scanner, nerlo-install-instruction
1 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: FILE_MAGIC_MISMATCH · Files: /repo/tests/fixtures/pi-guided-workflows/model/markdown-json-single-choice.txt · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
5 DATA_EXFIL_JS_NETWORK
Files: /repo/plugins/babel-fish/skills/visualize/scripts/publish-authored-html.js, /repo/share-server/src/index.ts · reported by cisco-skill-scanner
4 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/guide/scripts/fetch-anthropic-news.py · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/share-server, /repo/plugins/marvin, /repo · reported by cisco-skill-scanner
2 AAK-LEGAL-002
Files: share-server/package.json, plugins/babel-fish/skills/visualize/scripts/render-mindmap/package.json · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 ALLOWED_TOOLS_WRITE_VIOLATION
Files: /repo/plugins/babel-fish/skills/visualize/repo/plugins/babel-fish/skills/visualize/SKILL.md
86 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: TOOL_ABUSE_UNDECLARED_NETWORK, SOCIAL_ENG_VAGUE_DESCRIPTION, PIPELINE_TAINT_FLOW and 2 more · Files: /repo/repo/CONVENTIONS.md, /repo/plugins/guide/repo/plugins/guide/README.md, /repo/SKILL.md and 62 more · reported by cisco-skill-scanner, nerlo-install-instruction
55 The review call did not complete.
Rules: COMMAND_INJECTION_EVAL, COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_command_injection_generic and 14 more · Files: /repo/plugins/quellis-architect/hooks/lib/contract_loader.py, /repo/plugins/quellis-architect/hooks/lib/doctrine_loader.py, /repo/plugins/quellis-architect/hooks/lib/validate_pack.py and 19 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction and 1 more
3 The model did not answer for these findings.
Rules: AAK-HEALTHCARE-AI-004 · Files: plugins/deep-thought/knowledge/socratic-patterns.md, plugins/deep-thought/agents/cto-advisor.md, plugins/quellis/skills/coach/SKILL.md · reported by agent-audit-kit
Critical command injection, secret exposure, and SQL injection risks.
The artifact exhibits critical command injection vulnerabilities, including via `eval` and child processes, in files such as `/repo/plugins/quellis-architect/hooks/lib/contract_loader.py` and `/repo/plugins/babel-fish/skills/visualize/scripts/render-mindmap/index.js`. It also contains potential secret exposure in `plugins/quellis-architect/tests/test_pretool_match.py` and SQL injection vulnerabilities. Additional high and medium severity findings indicate capabilities for data exfiltration through file system access and network connections, alongside dynamic code execution.
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.
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.dippy · reported by cisco-skill-scanner
Showing 18 of 18; the rest are in the per-scanner reports above.