skills/zjy365/skills/ui-router/Gen Agent Trust Hub

ui-router

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The references/ui-skill-catalog.md file contains a curated list of external GitHub repositories that serve as sources for specialized UI capabilities. These include repositories from individual developers and organizations such as tw93/Waza, Leonxlnx/taste-skill, emilkowalski/skills, pbakaus/impeccable, ibelick/ui-skills, and heygen-com/hyperframes.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to take broad user requests for interface work and translate them into a sequence of tool invocations, which presents a potential injection surface.
  • Ingestion points: User-provided descriptions of UI tasks (e.g., "redesign", "build", "polish") enter the agent context to drive the routing logic in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific "ignore" markers for interpreting user requests when selecting skills.
  • Capability inventory: Based on the routing decision, the agent can recommend or invoke various specialized skills from the catalog, creating a multi-step execution chain across scripts and tools.
  • Sanitization: There is no evidence of input validation or sanitization applied to the user's request before it influences the selection of the primary and supporting skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:30 AM
Security Audit — agent-trust-hub — ui-router