agency-ui-finish-gate-reviewer
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests using an external resource at https://uizze.com for gathering design patterns.
- [PROMPT_INJECTION]: The skill processes user-provided implementation details and screens, which presents an indirect prompt injection surface.
- Ingestion points: The agent reviews implemented screens and user input as part of the 'Workflow Process' in SKILL.md.
- Boundary markers: No specific delimiters or instructions are used to distinguish untrusted UI text from the agent's core instructions.
- Capability inventory: The skill is primarily instructional and does not utilize tools for file system access, network requests, or command execution.
- Sanitization: The skill lacks explicit sanitization or validation mechanisms for the external UI content it analyzes.
Audit Metadata