The Agent Skills Directory

[SAFE]: The skill provides standard, idiomatic Python testing examples and documentation. All external package references such as pytest, sqlalchemy, and httpx are well-known and represent standard tools in the Python ecosystem. No hardcoded secrets, obfuscated content, or unauthorized network operations were found.
[INDIRECT_PROMPT_INJECTION]: The skill defines a standard attack surface for indirect prompt injection by instructing the agent to analyze and run Python test suites. * Ingestion points: User-supplied Python source files (test_*.py, conftest.py) and configuration files (pyproject.toml). * Boundary markers: The skill relies on standard Markdown code blocks for separating instructions from code content. * Capability inventory: The instructions facilitate the execution of the pytest CLI tool, which discovers and executes Python code in the local environment. * Sanitization: No explicit validation or filtering of the test file contents is defined.

pytest