openapi-spec-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting user-provided descriptions and source code to extract API definitions, which creates an indirect prompt injection surface. A user could include malicious instructions within code comments that might attempt to steer the agent's behavior. The risk is assessed as safe because the skill is restricted to text generation and lacks instructions for high-privilege tool usage.
- Ingestion points: The skill extracts endpoints, parameters, and models from natural language descriptions and source code across multiple programming languages and frameworks (SKILL.md).
- Capability inventory: Capabilities are limited to generating YAML/JSON specifications and providing summary tables (SKILL.md).
- Boundary markers: No specific boundary markers or instructions to disregard embedded commands in the input data are defined.
- Sanitization: The skill does not provide instructions for sanitizing user-supplied data before incorporating it into the final output.
Audit Metadata