api-sdk-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied API definitions or OpenAPI specifications to generate code, which introduces a potential for indirect instructions to influence the agent's output.
- Ingestion points: Processes external API documentation and specifications provided by the user (SKILL.md description).
- Boundary markers: The instructions lack specific delimiters or warnings for the agent to ignore instructions that might be embedded within the user's API documentation.
- Capability inventory: The skill is capable of generating functional Python and TypeScript code involving network requests (using
httpxandfetch) and file structure generation. - Sanitization: There is no evidence of input validation or sanitization for the content of the API specifications provided by the user.
Audit Metadata