test-driven-development
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute local testing commands as part of the development workflow.
- Evidence: Instructions to run
npm testinSKILL.mdto verify test states. - Context: This is standard behavior for TDD implementation and occurs within the local environment.
- [PROMPT_INJECTION]: The skill uses authoritative directives to modify the agent's typical code-handling behavior.
- Evidence: Phrases like 'The Iron Law' and 'Delete means delete' in
SKILL.mdinsist on the removal of code not backed by tests. - Context: These instructions are domain-specific for the TDD methodology and do not target safety filters or core agent guidelines.
Audit Metadata