create-memory
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill uses standard file system tools (Read, Write, Edit, Grep) to maintain local documentation in a specific directory ('.claude/memory/').
- [PROMPT_INJECTION]: Instructions are focused on task execution; no bypass or override attempts were found.
- [COMMAND_EXECUTION]: The use of 'grep' is limited to verifying successful file updates and does not involve untrusted inputs or high-privilege operations.
Audit Metadata