test-service
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
bundle exec rspecto verify test outcomes. This is the primary and expected function of a testing skill. - [PROMPT_INJECTION]: Instructions include enforcement terminology like 'HARD-GATE' and 'CRITICAL' to ensure the agent follows Test-Driven Development (TDD) workflows. These are benign procedural constraints and do not target the underlying AI safety filters.
Audit Metadata