skills/qu-skills/skills/agent-ui/Gen Agent Trust Hub

agent-ui

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of component definitions from "https://ui.inference.sh/r/agent.json" and the installation of the "@inferencesh/sdk" package from npm. These resources originate from the vendor's official infrastructure.
  • [COMMAND_EXECUTION]: Setup involves executing "npx" and "npm" commands to add the agent component and its associated SDK, which are standard procedures for React/Next.js development.
  • [PROMPT_INJECTION]: The component creates an interface for processing untrusted user input and interacting with browser UIs via client-side tools. 1. Ingestion points: User chat input and UI metadata. 2. Boundary markers: Configuration allows for a "system_prompt" to constrain agent behavior. 3. Capability inventory: Includes tools for UI manipulation like "scan_ui" and "fill_field". 4. Sanitization: Input handling is managed by the vendor's SDK and component logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:27 PM
Security Audit — agent-trust-hub — agent-ui