Healthcare Customer Service
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown-based instructions, character personas, and interaction templates.
- [SAFE]: No external dependencies or remote code execution patterns were identified. There are no calls to npm, pip, or remote shell scripts.
- [SAFE]: No obfuscation techniques such as Base64, hex-encoding, or hidden characters were found.
- [SAFE]: The instructions incorporate safety-first guidelines, specifically mandating clinical non-advice, identity verification for HIPAA compliance, and immediate redirection to emergency services (911/ER) for medical crises.
- [SAFE]: There are no signs of prompt injection or attempts to bypass agent safety filters; the instructions reinforce rather than override safety boundaries.
Audit Metadata