openapi-to-typescript
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied OpenAPI specifications (JSON/YAML) which represent a potential attack surface for indirect prompt injection. A maliciously crafted specification could contain instructions in descriptive fields designed to subvert the agent's logic during code generation or influence the file output path.\n
- Ingestion points: The skill reads an external OpenAPI specification file as directed by the user (SKILL.md).\n
- Boundary markers: There are no explicit instructions to treat the file content as untrusted data or use delimiters to prevent command leakage.\n
- Capability inventory: The skill possesses the capability to write files to the local file system (SKILL.md, Step 7).\n
- Sanitization: While the skill performs structural validation of the OpenAPI version, it lacks explicit sanitization or filtering of text fields that are interpolated into the generated TypeScript output.
Audit Metadata