ui
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which creates an indirect prompt injection surface.
- Ingestion points: Phase 1 involves reading UI content from screenshots, code, or descriptions provided by the user (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the user-provided UI data.
- Capability inventory: This skill does not directly perform subprocess calls, file writes, or network operations, but it invokes multiple external orchestrators (ux-orchestrator, copywriting-orchestrator) whose capabilities should be considered.
- Sanitization: There is no evidence of input validation or sanitization of the content before it is processed by the UX and copywriting modules.
Audit Metadata