The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes uvx --from lintlang==0.8.0 which may download the lintlang package from the Python Package Index (PyPI) if it is not already available in the local environment.
[COMMAND_EXECUTION]: The skill executes shell commands (lintlang --version and uvx ... lintlang scan) to perform its auditing functions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit local files (YAML, Markdown, Python, etc.) that may contain malicious instructions intended to influence the AI agent's behavior. Ingestion points: User-specified file paths passed as arguments to the audit command. Boundary markers: The instructions explicitly warn the AI to treat output such as evidence and description as untrusted content. Capability inventory: Shell execution of the lintlang tool and reporting of file contents. Sanitization: The instructions direct the agent to report specific finding codes rather than full content excerpts to minimize the risk of executing embedded instructions.

lintlang-audit