tdd
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides a set of instructional guidelines for Test-Driven Development (TDD), focusing on the Red-Green-Refactor cycle. These instructions are purely functional and do not contain malicious prompts or bypasses.
- [COMMAND_EXECUTION]: The skill directs the agent to run the project's test commands in the shell. This is standard behavior for testing tools and does not involve unauthorized privilege escalation or dangerous parameters.
- [SAFE]: The skill uses a tool (
mcp__x__ask_codex) to consult an external source for testing strategies. This use of external data is mitigated by specific instructions requiring the agent to form its own strategy first and to critically evaluate the external output, reducing the risk of indirect prompt injection.
Audit Metadata