The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to install and run the ruff tool (e.g., pip install ruff, ruff check .). These are standard operations for development workflows.
[EXTERNAL_DOWNLOADS]: The skill references downloading the ruff package from PyPI and using pre-commit hooks from the official Astral organization repository (github.com/astral-sh/ruff-pre-commit). These are well-known, trusted sources within the Python ecosystem.
[INDIRECT_PROMPT_INJECTION]: As a tool that processes source code, the skill has an attack surface where maliciously crafted comments in a codebase could theoretically attempt to influence an agent's reasoning when it reviews the linter's output. However, this is an inherent property of all code-analysis tools and not a specific vulnerability of this skill.

ruff