sdk-scaffolder
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted OpenAPI specification files provided by a user to generate SDK skeletons. This represents a surface for indirect prompt injection where a malicious specification could attempt to influence the agent's output.
- Ingestion points: Processes OpenAPI spec files as primary input (SKILL.md, Section 1).
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers for the input specification content.
- Capability inventory: The skill's capabilities are limited to writing files to the
docs/api-report/directory. No network operations, shell command executions, or dynamic code evaluation (eval/exec) were found in the skill definition. - Sanitization: The instructions do not explicitly mandate sanitization of the OpenAPI content before generating the report, though the output is directed to documentation files rather than executable scripts.
Audit Metadata