review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.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.
Run a council review of the current changes.
review_diff MCP tool (server cli-bridge) with cwd set to therepository root. Use base for a non-default base ref (e.g. main).
(single/majority/consensus). Consensus findings are the ones every model saw independently — treat those as the priority list.
on each (the council can be wrong; you are the editor, not a relay).
For security-sensitive changes, prefer the security_review tool — same flow, security-focused prompts plus a residual-risk section.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.