The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): The documentation in SKILL.md is strictly educational and contains no instructions that attempt to manipulate the AI agent's behavior or safety filters.
[COMMAND_EXECUTION] (SAFE): The test_runner.py script executes test commands (npm test, pytest, etc.) using subprocess.run with argument lists. This is a secure implementation that prevents shell injection.
[EXTERNAL_DOWNLOADS] (SAFE): Usage of npx is restricted to well-known testing frameworks like Jest and Vitest, which is standard behavior for development tools.
[DATA_EXPOSURE] (SAFE): The script only reads project configuration files (package.json, pyproject.toml) to identify frameworks and does not access sensitive system files or environment variables.

testing-patterns