pythonista-testing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill instructs the agent to run commands such as
pytest --cov=srcandgrep. While these are standard developer tools, they involve executing local project code to measure test coverage and searching file contents. - [PROMPT_INJECTION] (LOW): This skill exhibits an Indirect Prompt Injection surface (Category 8).
- Ingestion points: The skill reads external data from
tests/conftest.pyand other files within thetests/directory to identify fixtures and patterns. - Boundary markers: Absent. There are no explicit instructions for the agent to disregard or sanitize embedded prompts within the files it reads.
- Capability inventory: The skill utilizes subprocess calls to execute
pytestand utilizes file system discovery tools (ls,grep). - Sanitization: Absent. Content from analyzed files is pulled directly into the agent's context without filtering.
Audit Metadata