The Agent Skills Directory

[COMMAND_EXECUTION]: The skill enables the agent to execute code search, linting, and refactoring tasks using the ast-grep CLI tool. Examples include searching patterns (ast-grep run), applying structural rewrites (--rewrite), and scanning projects with rule files (ast-grep scan).- [EXTERNAL_DOWNLOADS]: The documentation provides standard installation instructions using official package managers cargo, npm, and pip, as well as a direct binary download from the ast-grep GitHub repository. These sources are official and well-known for this software project.- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection as it processes untrusted local source code. 1. Ingestion points: project source files (e.g., in src/) and configuration rule files. 2. Boundary markers: None explicitly defined. 3. Capability inventory: The skill performs file search and modification (via --rewrite and --update-all). 4. Sanitization: Structural matching provides inherent safety compared to regex, but the skill does not detail sanitization of untrusted code contents. This risk is considered standard for linting and refactoring tools.

ast-grep