tdd-guide
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automates testing tasks by executing a series of local Python scripts (such as test_generator.py and coverage_analyzer.py) and running standard test runners like npm or pytest within the agent's environment.
- [PROMPT_INJECTION]: The skill is designed to ingest and process external source code and specification files, which creates a surface for indirect prompt injection. 1. Ingestion points: User-provided source code files, feature specifications (specs/*.md), and test coverage reports (lcov.info). 2. Boundary markers: The instructions do not define specific delimiters to separate untrusted content from the agent's instructions. 3. Capability inventory: The skill can execute local Python scripts and shell commands. 4. Sanitization: There is no mention of sanitizing or validating the input data before processing.
Audit Metadata