probe-boundaries

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions (SKILL.md) are purely conceptual and guide the AI through a thought process for analyzing claims. There are no executable commands or tool invocations present.
  • [SAFE]: The README provides installation commands using standard package managers (npx) and links to the author's own GitHub repository for manual installation, which is a typical distribution method for these extensions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 09:13 AM
Security Audit — agent-trust-hub — probe-boundaries