ui-research
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to research and collect UI/UX examples from external websites such as Mobbin, Awwwards, and Dribbble. This process involves ingesting untrusted external data into the agent's context.
- Ingestion points:
Phase 2: ResearchandPhase 3: Collectsections inSKILL.mddirect the agent to browse and save content from external galleries. - Boundary markers: The instructions do not specify any delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the external content.
- Capability inventory: The skill is focused on documentation and analysis; it does not explicitly invoke shell commands or file-writing tools with the external data, though it utilizes the agent's web browsing capabilities.
- Sanitization: There are no instructions provided to sanitize or filter the data fetched from external sources before it is processed for the design brief.
Audit Metadata