The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/test_runner.py utility uses the subprocess module to execute test commands. It identifies the appropriate command (e.g., npm test, pytest) based on the presence of project-specific files like package.json or pyproject.toml. This behavior is expected for a test runner and is consistent with the Bash tool permission.- [PROMPT_INJECTION]: The script reads project configuration files to determine execution logic, which presents an indirect prompt injection surface.
Ingestion points: The script ingests data from package.json, pyproject.toml, and requirements.txt within the target project directory.
Boundary markers: No specific delimiters or safety instructions are used to separate configuration data from execution templates.
Capability inventory: The script can execute arbitrary shell commands and read local project files.
Sanitization: No sanitization is performed on the command strings or script names extracted from project files, though the script targets standard framework names by default.

testing-patterns