tdd
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions for an AI agent to follow a specific development process. No malicious code or suspicious patterns were found during the analysis.
- [COMMAND_EXECUTION]: The skill instructs the agent to identify and run standard development testing commands (e.g.,
npm test,pytest,cargo test,go test) and version control commands (git commit) based on the project environment. These commands are essential for the TDD workflow and do not involve arbitrary or obfuscated execution. - [PROMPT_INJECTION]: The skill uses a hook mechanism to monitor agent behavior and enforce the 'Red-Green-Refactor' process. It also presents a surface for indirect prompt injection as it processes project files.
- Ingestion points: Reads task descriptions and progress from local files
plan.mdanddoing.md(SKILL.md). - Boundary markers: No specific delimiters are defined to isolate file content from agent instructions.
- Capability inventory: Execution of project-defined test commands and git operations (SKILL.md).
- Sanitization: No explicit validation or escaping of input from project files is performed.
Audit Metadata