parkinsons-law
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides coaching instructions without executable scripts, network requests, or access to sensitive user data.
- [PROMPT_INJECTION]: The skill processes user-supplied project details which are used to generate a local file, representing an indirect prompt injection surface. 1. Ingestion points: User input for project names and tasks. 2. Boundary markers: No explicit markers are used to isolate user data. 3. Capability inventory: Local file-writing is used to save coaching reports. 4. Sanitization: No specific instructions are provided for validating user-supplied project names used in filenames.
Audit Metadata