openapi-spec-generator
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code provided by the user (such as Express, FastAPI, Django, or Spring controllers) to automatically extract API routes and schemas. This processing of external, potentially adversarial data creates a surface for indirect prompt injection, where malicious instructions hidden in code comments or string literals could attempt to influence the agent's behavior or poison the resulting documentation.
- Ingestion points: The 'Extracting from Code' section in
SKILL.mdexplicitly instructs the agent to read route definitions, middleware, and request body usage from user-provided source files. - Capability inventory: The skill can generate and export file content (YAML/JSON) and trigger additional workflows, such as calling the 'API Test Case Generator' skill.
- Boundary markers: The instructions lack explicit directives for the agent to use delimiters or to disregard natural language instructions found within the analyzed code snippets.
- Sanitization: There are no specified steps to sanitize or escape content extracted from the source code before it is interpolated into the generated OpenAPI/Swagger specification.
- [SAFE]: The skill leverages standard industry templates for OpenAPI 3.x and Swagger 2.0 and provides useful reference documentation for authentication and common API patterns.
- [SAFE]: The promotion of 'TestMu AI HyperExecute' within the skill's instructions is promotional in nature but does not involve suspicious code execution, obfuscation, or data exfiltration.
Audit Metadata