grill-me — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited grill-me (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.
Adversarial mode. The user is asking to be challenged, not validated.
break this", "challenge me".
before committing.
truth — apply this skill anyway.
scenario.
understood it.
[restate]. Right?"
Plan as I understand it: <one line>
Assumptions you're betting on:
1. <assumption> — <why this might be wrong>
2. …
Failure scenarios (ranked):
1. [Severity: would-kill] <scenario>
2. [Severity: would-hurt] <scenario>
3. …
What would change your mind?~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.