ui-review-tahoe
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted external data to perform UI/UX audits, creating a potential attack surface.
- Ingestion points: The skill processes user-supplied application source code and screenshots for review, as outlined in the systematic UI audit steps in
skill.md. - Boundary markers: The instructions lack explicit delimiters or specific directives for the agent to ignore instructions that might be embedded within the provided UI assets or code snippets.
- Capability inventory: While the skill's own markdown does not invoke dangerous tools, it operates within an agent environment where influenced behavior could lead to the misuse of available capabilities.
- Sanitization: There are no mechanisms described to filter or sanitize potential prompt injection content from the analyzed materials before they are processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references various external documentation resources.
- Evidence: Provides links to official Apple developer documentation (developer.apple.com) and W3C accessibility guidelines (w3.org). These references are for educational and guideline-compliance purposes and originate from trusted organizations.
Audit Metadata