skills/dickwu/mem-setup/mem-save/Gen Agent Trust Hub

mem-save

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or high-risk behaviors were detected. The skill uses standard file operations for documentation purposes.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by summarizing potentially untrusted codebase content into persistent knowledge files.
  • Ingestion points: Insights are derived from the "current work" (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Writing to markdown files within the /knowledge/ directory.
  • Sanitization: The skill incorporates a manual verification step ("Ask Before Saving") which allows the user to review and sanitize insights before they are persisted.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 03:11 AM
Security Audit — agent-trust-hub — mem-save