tdd-workflow
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary purpose is providing educational guidance on TDD practices, which is reflected in its content and examples.
- [COMMAND_EXECUTION]: Instructs the agent on how to use standard command-line tools for development, including package-specific test runners (npm, pytest, cargo), version control (git), and text search utilities (grep, ripgrep).
- [EXTERNAL_DOWNLOADS]: References a public GitHub repository and suggests adding a third-party testing utility ('tdd-guard') via standard dependency management tools.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it reads local source files to determine existing behaviors, though this is typical for development-oriented agents.
- Ingestion points: Reads local code and test files using 'glob' and 'ripgrep' patterns in SKILL.md.
- Boundary markers: None present.
- Capability inventory: Executes local shell commands and test runners.
- Sanitization: None present.
Audit Metadata