openapi-spec-generator
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied source code and natural language descriptions to generate API specifications.
- Ingestion points: User-provided source code (Express, FastAPI, Django, Spring Boot, Rails) and partial specifications are processed in Step 1 and the "Extracting from Code" section to extract endpoints and models.
- Boundary markers: The instructions lack specific boundary markers or directives to explicitly tell the agent to ignore instructions that might be embedded within the user-provided source code provided for analysis.
- Capability inventory: The skill generates file outputs (.yaml, .json) and has the capability to transition to another skill (API Test Case Generator) to process the generated output.
- Sanitization: There is no mention of sanitizing, escaping, or validating the input code or descriptions before they are interpolated into the prompt or processed by the agent.
Audit Metadata