context-diet
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a verification block that creates a local JSON file ('mcp-config.json') and executes a Node.js script to validate the file schema. This logic is benign and restricted to local validation.
- [SAFE]: The skill references a local binary path ('/usr/local/bin/codebase-memory-mcp') and an external documentation URL ('flowstacks.xyz'), but it does not perform automated downloads or execute remote code.
Audit Metadata