The Agent Skills Directory

[SAFE]: The skill provides high-level instructions for a common development task. It does not include any scripts, executable code, or remote downloads. The use of frontmatter configuration to disable model invocation is a safety-enhancing restriction that prevents the agent from making model calls during the execution of this task.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface as it is designed to process external code and tool outputs. 1. Ingestion points: The agent reads the repository's source code and the stdout/stderr of linting commands (SKILL.md). 2. Boundary markers: No explicit delimiters are specified for separating the linter's output from the agent's instructions. 3. Capability inventory: The agent is authorized to run project-defined lint commands and modify files to apply fixes. 4. Sanitization: No sanitization logic is provided. This represents a typical operational risk for agents performing automated code maintenance.

w-lint