mem-monthly
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted data from the
AI_MEMORY/L2_行为层/directory. * Evidence Chain: 1. Ingestion point: All files inAI_MEMORY/L2_行为层/(SKILL.md). 2. Boundary markers: None identified. 3. Capability inventory: Reads local files and writes toL3_认知层/andMeta/复盘记录.md. 4. Sanitization: No evidence of input filtering or escaping before processing behavior logs.
Audit Metadata