github-search — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited github-search (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.
Utility skill that bridges conversation corpus ↔ code corpus. Four modes project different joins. Every result IS a citation (repo + commit SHA, or conv_id).
mode=validate)query: str = ""
project: str | None
mode: "timeline" | "conversations" | "code" | "validate" = "timeline"
limit: int = 10Mode-specific markdown. Always includes: repo name, commit timestamp (when applicable), conv_id (when applicable).
validate mode surfaces the predates-project warning when a conversation predates the earliest committimeline mode shows repo created_at + commits DESCcode mode uses semantic search across commit messages~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.