stitch-ui-design-spec-uviewpro
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied design requests and interpolates them into prompt templates for the Stitch system. It utilizes clear boundary markers like
[Context],[Layout], and[Components]to structure the output. While this creates an ingestion surface for potentially untrusted data, the skill does not contain executable logic that would escalate this surface to a high-risk vulnerability. Capabilities includeReadandWritetool access, but no dynamic execution of input is performed within the skill's scripts. - [EXTERNAL_DOWNLOADS]: The skill references official documentation and resource URLs for the uView Pro framework (
uviewpro.cn). These references are informative and point to the official site of the technology being documented, which is standard practice for design specification skills.
Audit Metadata