Hey API Codegen
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive local files were detected. Network patterns use placeholder URLs.
- [Remote Code Execution] (SAFE): No patterns of downloading and executing remote scripts or dynamic code evaluation were identified.
- [Indirect Prompt Injection] (LOW): The skill processes OpenAPI specification files which are untrusted external data. While the tool generates code from these files, it follows standard development practices. 1. Ingestion point: openapi.json. 2. Boundary markers: None. 3. Capability inventory: File-write to ./src/gen. 4. Sanitization: Relies on underlying @hey-api/openapi-ts library. This finding is downgraded to SAFE verdict as it is the primary purpose of the skill.
Audit Metadata