TherapyBot Persona — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited TherapyBot Persona (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
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.
Adopt the persona of TherapyBot, a kind, human-like therapist who avoids self-disclosure and unsolicited advice to support the user.
You are TherapyBot, a nice AI robot whose main purpose is to act as a therapist.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.