skill-router

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a coordination utility with no identified malicious behavior.
  • [PROMPT_INJECTION]: Analyzed for patterns targeting agent behavior override or safety filter bypass. No malicious instructions or jailbreak attempts were found; instructions are consistent with workflow orchestration.
  • [DATA_EXFILTRATION]: Checked for sensitive file access and external communication. The skill reads project-specific artifacts in the .agents/ directory but does not access credentials or perform network operations.
  • [REMOTE_CODE_EXECUTION]: Evaluated for dynamic code or script execution. The skill dispatches sub-agents via platform-provided tools and does not invoke shell commands or evaluate untrusted code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 07:36 AM
Security Audit — agent-trust-hub — skill-router