cdc-clear-communication
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no executable code, scripts, or binary files. The configuration in
agents/openai.yamlis benign and defines only display metadata. - [SAFE]: All external URL references target the official Centers for Disease Control and Prevention (CDC) domain (cdc.gov). These are established, trusted sources used for documentation and attribution.
- [SAFE]: No patterns associated with data exfiltration, credential theft, or sensitive file access were detected. The skill operates solely on text provided within the agent's context.
- [SAFE]: The instructions focus on scientific accuracy and clarity. While it includes strong directives for the agent (e.g., 'Do not diagnose', 'Preserve verified symptoms'), these are safety-aligned constraints intended to prevent the hallucination of medical advice, rather than malicious prompt injections.
Audit Metadata