knowledge-consolidation
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill describes a system for ingesting and storing user-provided observations which can influence future agent sessions. 1. Ingestion points: User phrases like 'remember this' or 'learned'. 2. Boundary markers: None mentioned for the stored data. 3. Capability inventory: Uses tools like 'memory_sessions' and 'reasoning_query' for persistence. 4. Sanitization: No sanitization logic is provided in the instructions.
- [No Code] (SAFE): The skill consists entirely of markdown instructions and does not include any executable scripts, binary files, or external package dependencies.
Audit Metadata