send-experiment-designer
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected across any threat categories.
- [SAFE]: The skill correctly handles the attack surface of untrusted data ingestion (ESP exports) by providing clear boundary instructions and treating data as non-executable values.
- [SAFE]: The instructions explicitly forbid the use of external code or scripts for data processing, reducing the risk of remote code execution or dynamic execution vulnerabilities.
Audit Metadata