openapi-to-application-code
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external and potentially untrusted OpenAPI specifications provided via URL, file path, or direct text input.
- Ingestion points: The skill ingests data during 'Step 1: Analyze the OpenAPI Specification' and 'Step 3: Generate Application Code'.
- Boundary markers: The instructions do not include specific delimiters or warnings for the agent to ignore natural language instructions that may be embedded within the OpenAPI document's fields (such as
description,title, orsummary). - Capability inventory: The skill directs the agent to create a complex directory structure and multiple source files across the local filesystem, which could be abused if the agent follows malicious instructions hidden in the specification.
- Sanitization: There is no explicit requirement for the agent to sanitize or validate the content of the OpenAPI specification to prevent prompt injection attacks.
Audit Metadata