api-documentation
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as API specifications and source code, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill accepts OpenAPI/Swagger specifications, router handler code, and GraphQL schemas as input (SKILL.md).
- Boundary markers: There are no explicit instructions to use delimiters or warnings to ignore instructions embedded within the user-provided API specifications.
- Capability inventory: The skill's primary function is text generation; however, it includes logic to chain the output into an 'API Test Case Generator' skill, which could propagate malicious instructions if the input is not sanitized.
- Sanitization: The instructions do not specify a requirement to sanitize or validate the content of descriptive fields (like 'description' or 'summary') within the ingested API definitions.
Audit Metadata