hai-ast-grep
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external source code, which represents a potential ingestion point for malicious instructions intended to manipulate the agent's search or rewrite logic.
- Ingestion points: Target source code files (e.g.,
src/directory). - Boundary markers: The instructions do not define explicit delimiters for ingested code but emphasize a 'canonical workflow' requiring validation against positive and negative fixtures to prevent false matches.
- Capability inventory: The skill utilizes
ast-grepwhich possesses capabilities to read from and write to the local filesystem (e.g.,-U,--update-all, andfix:configurations). - Sanitization: Mitigation is provided through mandatory validation steps, interactive review flags (
-i), and dry-run procedures before applying mass changes.
Audit Metadata