test-runner

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and commands represent standard development workflows for test execution, failure diagnosis, and coverage analysis.
  • [COMMAND_EXECUTION]: The skill provides examples of standard shell commands for testing tools including jest, pytest, cargo, and go test. These are necessary for the skill's primary function and do not exhibit dangerous patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions for analyzing test failure logs and error patterns.
  • Ingestion points: The agent reads shell output from testing frameworks (e.g., AssertionError, TimeoutError).
  • Boundary markers: Not explicitly defined in this instructional skill.
  • Capability inventory: The skill can run test commands, check environment variables (pip list, npm list), and generate coverage reports.
  • Sanitization: No explicit sanitization of test output is described; however, the pattern matching used for diagnosis is a common and expected feature of testing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:16 AM
Security Audit — agent-trust-hub — test-runner