enhance-claude-memory
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill provides guidelines and patterns for improving documentation files used by AI assistants, which is a benign and helpful function.\n- [SAFE]: File access is limited to project documentation and configuration files (e.g., README.md, package.json, and memory files), which is consistent with the skill's primary purpose and involves no sensitive credential paths.\n- [PROMPT_INJECTION]: The skill processes untrusted instructions from memory files as a surface for indirect prompt injection; however, it only performs read-only analysis and reporting, posing no functional risk.\n
- Ingestion points: CLAUDE.md, AGENTS.md, README.md, package.json.\n
- Boundary markers: Absent.\n
- Capability inventory: The skill is limited to read-only analysis and does not request capabilities for file writing, network access, or command execution.\n
- Sanitization: Absent.
Audit Metadata