The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and audit Python source files, which serves as an ingestion point for potentially untrusted data.
Ingestion points: Files matching the glob pattern **/*.py processed by the agent using this skill.
Boundary markers: The instructions do not define explicit boundary markers or delimiters for user-provided code content.
Capability inventory: The skill provides instructions for writing and executing tests, which typically involve environment-side execution via pytest. The skill itself does not perform subprocess calls or network operations directly.
Sanitization: No specific sanitization or filtering of input code comments or metadata is implemented.
[SAFE]: The skill references standard, well-known Python packages for testing (pytest, pytest-cov, pytest-asyncio, pytest-mock, pytest-xdist) and uses official GitHub Actions from the actions organization.

python-testing