ui-designer
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external URLs provided as arguments using the
WebFetchtool for visual design audits. This creates a surface for indirect prompt injection if the fetched content contains malicious instructions intended to influence the agent's behavior. - Ingestion points:
SKILL.mdtriggers an ingestion process when a URL is passed as an argument, utilizing theWebFetchtool. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potential instructions embedded within the external content being analyzed.
- Capability inventory: The skill has access to powerful tools including
Bash,Read,Grep,Glob,WebFetch, andWebSearch. - Sanitization: No specific sanitization or filtering of external content is defined before the agent processes it for design feedback.
Audit Metadata