how-it-works

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of descriptive text explaining tool behavior and data privacy practices. It does not contain any executable scripts, shell commands for the agent to run, or prompt injection patterns.
  • [EXTERNAL_DOWNLOADS]: The documentation mentions the claude-mem package and standard AI providers (Claude, OpenRouter, Gemini), which are transparently disclosed as part of the tool's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 12:55 AM