api-tester
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including OpenAPI/Swagger files, source code (controllers, handlers), and existing test files which could serve as vectors for indirect prompt injection attacks.
- Ingestion points: Reads project files such as
OpenAPI / Swagger,routes,controllers,existing API tests, anddocumentsto extract API contracts. - Boundary markers: The instructions emphasize verifying evidence against actual implementation but do not define strict delimiters or sanitization routines for the content of the files being parsed.
- Capability inventory: The agent is authorized to generate code (file writing) and execute test scripts (shell command execution) based on the parsed data.
- Sanitization: There is no specific mention of sanitizing or escaping the content of the ingested project files before it is processed by the LLM logic.
Audit Metadata