agent-test
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The shell script located at
evals/run-static-checks.shexecutes a local Python script (check-skill-static.py) intended for validating the consistency and structure of the skill repository. This command operates within the local environment on local files and does not involve network access or the processing of untrusted remote data. - [SAFE]: A comprehensive review of the markdown instructions, reference materials, and JSON metadata confirms the absence of malicious patterns. There are no signs of prompt injection, credential exfiltration, obfuscation, or unauthorized dependency management. The skill functions primarily as a knowledge base for evaluating agent performance.
Audit Metadata