diagnose-generation-failure
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill handles untrusted data in the form of OpenAPI specifications, which could potentially contain malicious instructions aimed at the agent. Ingestion points: The
<spec-path>and the content of spec files are ingested during linting and inspection steps. Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between data and commands within the spec files. Capability inventory: The skill utilizes shell commands (speakeasy,yq,jq) which can read and process local files. Sanitization: There are no instructions for validating or sanitizing the input file paths or their contents before execution.
Audit Metadata