maintaining-memory-md
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and configuration metadata without any executable scripts, subprocess calls, or code blocks.
- [SAFE]: The instructions include explicit security prohibitions against storing sensitive data such as credentials, API keys, and personal information within the MEMORY.md file.
- [SAFE]: No network operations, external downloads, or third-party package dependencies are referenced or utilized.
- [SAFE]: The skill implements a 'source of truth' check, instructing the agent to prioritize current repository evidence over potentially stale or incorrect memory entries.
Audit Metadata