zod-extract
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on local source code files, which serves as an ingestion point for untrusted data.
- Ingestion points: The skill searches for Zod schema patterns across the project's source files.
- Boundary markers: The instructions do not define specific markers to isolate the analyzed code from the agent's instructions.
- Capability inventory: The skill has file system read and write capabilities to create validations/ files and modify existing source files.
- Sanitization: No specific sanitization or validation of the extracted code blocks is mentioned.
Audit Metadata