brain
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for knowledge management and persistent memory by reading and writing files within a local
brain/directory. It establishes rules for file naming, linking, and organizational structure. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the
brain/directory which could potentially contain instructions that influence the agent in future sessions. However, this is the core intended functionality of a persistent memory skill. The instructions emphasize quality control and relevance to mitigate the impact of low-quality or speculative content entering the vault.
Audit Metadata