eva
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill consists exclusively of Markdown-based instructions and modular logic for conversational AI guidance.
- [SAFE]: No network operations, remote script execution, or external dependencies are present in any of the skill files.
- [SAFE]: The 'sediment mechanism' for data persistence uses local, user-specific paths (e.g.,
~/.eva/sessions/) for session management and does not involve exfiltration of sensitive information to external servers. - [SAFE]: The skill includes explicit safety-conscious steering, such as 'hard gates' for title verification and clear instructions to avoid fabricating data, personal experiences, or data metrics.
Audit Metadata