ui-designer
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources which creates an attack surface where malicious instructions could be embedded in the data being analyzed.
- Ingestion points: The skill accepts a URL, component name, or file path as an argument (
argument-hint) and usesWebFetchandReadto bring that content into the agent's context for evaluation (Step 0 and Step 0.5). - Boundary markers: There are no explicit instructions to use delimiters or to ignore potential instructions contained within the fetched HTML or source code.
- Capability inventory: The skill has access to
Bash,WebFetch,Read, andWebSearchtools, allowing it to execute shell commands and perform network operations. - Sanitization: The instructions do not specify any validation or filtering for the external content before the agent processes it for design auditing.
Audit Metadata