stitch-ui-design-spec-generator
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from natural language requests and PRD documents (Type A and Type B inputs).
- Ingestion points: User-supplied natural language strings and content from PRD files or text blocks specified via file paths.
- Boundary markers: The instructions lack explicit boundary markers or directives to ignore embedded instructions within the processed data (e.g., instructions to ignore specific headers or non-functional requirement sections).
- Capability inventory: The skill has no
allowed-toolslisted and performs no direct system actions. Its primary output is a JSON design specification intended for use by thestitch-ui-prompt-architectskill. - Sanitization: There is no mention of input sanitization or validation of the content extracted from PRDs to prevent downstream prompt manipulation.
Audit Metadata