med-health

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are focused entirely on journalistic methodologies, medical ethics, and statistical accuracy. No patterns of prompt injection, data exfiltration, or malicious command execution were found.
  • [SAFE]: The skill defines a strict 'Iron Law' for risk communication to prevent misleading reporting. It includes explicit warnings against providing medical advice and redirects users to healthcare providers for personal health concerns.
  • [SAFE]: All external references are to legitimate health and medical authorities (WHO, CDC, Ministry of Health, etc.). No obfuscated URLs or suspicious remote code patterns are present.
  • [SAFE]: The skill does not request or use any sensitive tools or system permissions. It operates as a text-processing assistant for drafting and auditing news stories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:15 AM
Security Audit — agent-trust-hub — med-health