python3-tdd
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied feature descriptions via the $ARGUMENTS variable to drive the TDD workflow steps.
- Ingestion points: The skill interpolates $ARGUMENTS directly into the Task field in SKILL.md.
- Boundary markers: There are no explicit delimiters or protective instructions (e.g., 'treat this as data') surrounding the user input.
- Capability inventory: The agent is instructed to write implementation code and execute shell commands (pytest, ruff, prek) based on these descriptions.
- Sanitization: No sanitization or validation of the task description is implemented.
- [COMMAND_EXECUTION]: The skill uses the uv toolchain to execute local development and quality assurance tools.
- Commands executed include uv run pytest, uv run ruff, and uv run prek for testing, linting, and formatting.
- These actions are consistent with the skill's stated purpose of guiding a Python TDD cycle.
Audit Metadata