The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided Python source code to generate corresponding test suites. This creates an attack surface where instructions embedded in the code under test could influence the agent's behavior. However, this is inherent to the skill's purpose, and the documentation does not suggest auto-executing this code without human review.
[EXTERNAL_DOWNLOADS]: The documentation recommends the use of standard development dependencies and plugins (e.g., pytest-cov, hypothesis, pytest-xdist) using the uv package manager. These libraries are industry standards for Python testing and are fetched from public registries.
[DYNAMIC_EXECUTION]: The skill provides technical patterns for runtime module mocking (modifying sys.modules) and monkey-patching environment-checking functions. These techniques are documented as specific solutions for isolating heavy dependencies like scipy or ortools to improve test suite performance, which is a recognized practice in Python test infrastructure.

python-tdd