qa-agent-testing
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for designing evaluation suites and does not contain any executable code that performs network operations, file system modifications, or unauthorized data access.
- [SAFE]: It explicitly incorporates security-positive recommendations, such as testing for prompt injection, implementing tool sandboxing, and treating external tool outputs as untrusted.
- [SAFE]: No evidence of obfuscation, hardcoded credentials, or data exfiltration was found in the documentation or metadata.
- [SAFE]: The skill mentions a local Python script (
scripts/score_suite.py) for scoring, which is a standard utility function for a testing harness.
Audit Metadata