requesting-code-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited requesting-code-review (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.
You are biased toward your own work — you test what you built, not what's required. A fresh-eyes pass catches what you can't see. Do this before finalizing anything non-trivial.
git diff is clean, tests pass.Agenttool) and give it ONLY: the diff, the original requirement, and the instruction to review for correctness, edge cases, security, missing tests, and clarity — and to try to REFUTE that the change is correct. Don't tell it your conclusions.
(correctness / security / does-it-actually-meet-the-requirement). Majority skepticism wins.
assertion. Distinguish blockers from nits.
and what you changed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.