test-audit

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide structured feedback on test suites by analyzing existing code against a set of heuristics. It relies on local CSV routers and Markdown templates to guide its analysis and report generation.
  • [COMMAND_EXECUTION]: The skill includes a shell script (evals/run-static-checks.sh) used for development-time static verification. This script executes local commands and Python scripts using relative paths but is not part of the runtime instructions provided to the agent for processing user requests.
  • [DATA_EXFILTRATION]: The skill processes user-supplied test files and writes audit results to the local filesystem in specific directories (e.g., docs/audits/). It does not perform network operations or attempt to access sensitive system or credential files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 02:22 AM
Security Audit — agent-trust-hub — test-audit