not-to-do-list
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected.
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by reading external data from 'lifestyle-design.md'. However, the risk is negligible as the skill lacks high-privilege capabilities. * Ingestion points: Reads 'lifestyle-design.md' (if present) to customize advice. * Boundary markers: Absent. * Capability inventory: File write to 'not-to-do.md'. * Sanitization: Absent.
- [DATA_EXPOSURE]: The skill interacts with local productivity tracking files. It does not attempt to access credentials, private system configurations, or environment variables.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, external downloads, or third-party package dependencies were found.
Audit Metadata