using-git — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited using-git (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Treat git history as a record someone will read later. Commit and push only when the user asks; if you're on the default branch, branch first.
Committing
git status, git diff --staged). Stageonly related changes — one logical change per commit. Don't git add -A blindly.
imperative ("Fix …", "Add …"); body for the why if non-obvious.
Branches & PRs
tested. Confirm with the user before pushing or opening it (it's outward-facing).
Safety
published history without explicit confirmation. Prefer revert over reset for anything already pushed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.