skill-lookup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-lookup (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill to search a skill registry, inspect candidate skills, and install selected skills into a concrete <skill-root> without assuming a specific assistant or editor.
Use this skill when the user wants to:
search_skills using the user's task, domain, and likely triggers.get_skill.<skill-root> for installation.SKILL.md and any companion files under <skill-root>/{slug}/.SKILL.md is present and that the frontmatter is intact.search_skills: Search for skills by keyword, category, or tagget_skill: Retrieve one skill with all files and metadataquery should reflect the user's actual problem, not just a generic domain labellimit should stay small enough to review meaningfullycategory and tag filters are optional refinements, not mandatory inputs<skill-root> chosen for the current environmentsearch_skills({"query": "code review", "limit": 5, "category": "coding"})get_skill({"id": "abc123"})<skill-root>/skill-slug/
├── SKILL.md
├── reference.md
└── scripts/<skill-root>/{slug}/SKILL.md exists after installationFollow the constraints, conventions, and cautions documented below, and prefer the documented path over improvisation.
Use any linked scripts, assets, reference files, and companion resources mentioned in this document.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.