The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted local data (Python source files) which could contain adversarial instructions intended to influence the agent's actions.
Ingestion points: The agent reads the content of local Python files when executing commands like ruff check and ruff format.
Capability inventory: The skill allows file system modifications via ruff check --fix and ruff format.
Boundary markers: No specific delimiters or safety instructions are provided to help the agent distinguish between code content and potential instructions embedded in code comments.
Sanitization: No sanitization is performed on the files being processed, as the tool is intended to evaluate raw source code.
[EXTERNAL_DOWNLOADS]: The skill references uvx ruff and uv run ruff, which may trigger the download of the Ruff binary or its dependencies from official package registries. As Ruff is a well-known development tool maintained by a recognized organization (Astral), these operations are considered standard functional behavior.

ruff