memory
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard documentation and context-maintenance tasks. It operates on non-sensitive project metadata and markdown files.
- [DATA_EXFILTRATION]: The skill includes strong negative constraints, specifically directing the agent not to store secrets, tokens, or private URLs in the documentation it manages.
- [PROMPT_INJECTION]: While the skill ingests data from configuration files and chat history, it does so to maintain project context (purpose and tech stack). There are no instructions aimed at overriding safety guidelines or bypassing constraints.
Audit Metadata