skill-router

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a meta-instruction layer for task planning and orchestration. It does not include executable code, external scripts, or network communication logic.
  • [PROMPT_INJECTION]: Instructions focus on improving accuracy in skill selection. There are no attempts to override safety filters, pretend to be an unrestricted AI, or bypass system constraints.
  • [DATA_EXFILTRATION]: The protocol involves scanning descriptions of available skills, which is a standard discovery process. It does not access sensitive user data, environment variables, or private configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 03:01 PM
Security Audit — agent-trust-hub — skill-router