when-to-write-tests

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions that attempt to override other potential agent behaviors and systemic guidelines. It explicitly lists several other agent components (such as 'test-driven-development', 'using-superpowers', and 'definition-of-done') and mandates that 'this preference wins' over their instructions.
  • [PROMPT_INJECTION]: The skill employs meta-instruction techniques to influence the agent's priority hierarchy, stating 'User instructions beat skills. This preference is a user instruction,' which is a pattern used to bypass default agent constraints or conflicting instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:51 AM
Security Audit — agent-trust-hub — when-to-write-tests