superpowers-tdd
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is limited to instructional best practices for software development workflows, providing a structured approach for feature implementation and bug fixing.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process that involves ingesting and executing user-provided code (tests and linters) through shell commands. This is a standard surface for indirect injection but is inherent to the primary purpose of a TDD skill.
- Ingestion points: Local source code and test files referenced in the Red/Green/Refactor process.
- Boundary markers: Not present in the instructions.
- Capability inventory: Command execution via shell to run test suites and linters.
- Sanitization: Not explicitly defined in the skill instructions.
Audit Metadata