ui-review
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external UI data and design documentation which could theoretically contain instructions designed to influence agent behavior. 1. Ingestion points: docs/design.md and the implemented route or screen (SKILL.md). 2. Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within the reviewed content. 3. Capability inventory: Uses browser-testing and visual-taste tools for interface assessment (SKILL.md). 4. Sanitization: Absent; the skill does not specify validation or sanitization for the reviewed content.
Audit Metadata