ast-grep
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [SAFE]: The skill provides instructions for using ast-grep, a structural code search tool. The usage patterns (Bash and PowerShell) are standard for developer tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code from external repositories using tools like Read, Grep, and ast-grep. While this presents an attack surface where malicious code comments could attempt to influence the agent, the skill defines clear workflows and triage steps to minimize unintended behavior.\n
- Ingestion points: File content read via Read, Grep, and ast-grep (SKILL.md).\n
- Boundary markers: None explicitly defined for search results, though rule fixtures are encouraged.\n
- Capability inventory: Bash, Write, Read, Glob, Grep (SKILL.md).\n
- Sanitization: The skill relies on standard tool outputs and does not specify custom sanitization for repository content.\n- [DYNAMIC_EXECUTION]: The skill uses the Write tool to create YAML rule files on disk, which are then executed by the ast-grep CLI. This is a core feature of the tool and uses static templates or user-defined patterns rather than untrusted remote content.
Audit Metadata