scientific-clarity-checker
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No malicious patterns detected. The resource files consist exclusively of markdown documentation and a JSON-formatted rubric for evaluating scientific text.\n- Indirect Prompt Injection (LOW): This skill is designed to process untrusted external data (scientific documents). While the provided files lack boundary markers for untrusted input, they also contain zero executable capabilities (no file system access, no network operations, and no command execution). Consequently, the risk is limited to local influence on the agent's reasoning without external side effects.
Audit Metadata