setup-project-memory
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data by scanning local folders and repository configurations to populate templates. 1. Ingestion points: Local filesystem paths defined in SKILL.md. 2. Boundary markers: Instructions explicitly sandbox operations to a 'project-memory/' folder. 3. Capability inventory: File system read and write capabilities. 4. Sanitization: Manual review of drafts and explicit user confirmation are required before any write operations occur.
- [SAFE]: Hardcoded paths and file structures relate to the author's personal workflow and do not target sensitive system data.
- [SAFE]: No network activity, external script execution, or persistence mechanisms were detected.
Audit Metadata