evanflow-compact

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is purely instructional and guides the agent on how to manage its internal context and persistent memory files.
  • [DATA_ACCESS]: The skill references standard memory storage paths (e.g., ~/.claude/projects/<project>/memory/) used by the host platform. These access patterns are consistent with the skill's stated purpose of session state management and memory persistence.
  • [USER_CONTROL]: The skill explicitly mandates that sensitive actions, such as resetting the session context (/clear) or committing changes, must be initiated or approved by the user, adhering to the principle of least autonomy for destructive operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 11:33 AM