typed-service-contracts
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of educational documentation and code snippets promoting secure software development practices. No malicious code, obfuscation, or unauthorized data access patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an architecture for processing untrusted data inputs. (1) Ingestion points: The spec.ts template defines MyTaskInputSchema as the entry point for external data. (2) Boundary markers: The pattern enforces the use of Zod schemas to parse and validate all inputs before they reach business logic. (3) Capability inventory: The implementation example in handler.ts utilizes the Node.js fs module to check file existence. (4) Sanitization: The skill explicitly demonstrates sanitization techniques, such as path traversal checks using Zod refinements to ensure input strings do not contain dot-dot-slash patterns.
Audit Metadata