context-management
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill defines tools for ingesting project data without providing boundary markers or sanitization. 1. Ingestion points: Read, Glob, and Grep tools. 2. Boundary markers: Absent. 3. Capability inventory: Write tool allowed. 4. Sanitization: Absent.
- [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and contains no executable code.
Audit Metadata