hermes-profile-audit
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily composed of instructions and uses Python scripts only for offline validation. No runtime execution of untrusted code or network requests occur.
- [SAFE]: Included scripts (validate_bundle.py, test_contracts.py) rely solely on the Python standard library and include internal checks to ensure no hardcoded secrets or sensitive developer paths are present in the skill files.
- [PROMPT_INJECTION]: Instructions explicitly define an 'Untrusted Content Boundary' to prevent the agent from executing commands or revealing secrets contained within the audited materials.
- [CREDENTIALS_UNSAFE]: The skill proactively implements regex-based scanning for API keys and tokens in its own codebase to prevent accidental credential exposure.
Audit Metadata