The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface by processing external codebase content during linting and formatting tasks.
Ingestion points: The agent reads and acts upon source code files within the local environment as described in SKILL.md.
Boundary markers: There are no explicit delimiters or specific warnings to ignore embedded instructions within the processed code files.
Capability inventory: The skill allows the agent to execute tools such as lintro, ruff, black, and eslint and grants permission to modify files during the formatting process.
Sanitization: The skill relies on standard tool parsers and does not specify additional sanitization for the code being processed.
[EXTERNAL_DOWNLOADS]: The skill references a repository for its primary linting tool.
Evidence: The skill documentation points to https://github.com/lgtm-hq/py-lintro as the source for the preferred lintro utility.
[COMMAND_EXECUTION]: The skill defines several command-line operations required for its core functionality.
Evidence: The skill specifies the execution of uv run lintro fmt, uv run lintro chk, and uv run lintro tst, along with native tools like ruff, black, clippy, and eslint.

lint