spec-kitty-accept — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited spec-kitty-accept (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 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.
Source: This skill augments the baseline workflow located at ./workflows/spec-kitty.accept.md. It acts as an intelligent wrapper that is continuously improved with each execution.<!-- spec-kitty-command-version: 3.0.3 --> Run this exact command and treat its output as authoritative. Do not rediscover context from branches, files, or prompt contents.
spec-kitty agent shim accept --agent windsurf --raw-args "$ARGUMENTS"
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.