skills/kobe4cn/a2ui_skills/a2ui/Gen Agent Trust Hub

a2ui

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill is composed of protocol documentation and implementation guides. Analysis confirmed the absence of prompt injection, obfuscation, persistence mechanisms, or unauthorized data access patterns.
  • [Indirect Prompt Injection] (LOW): The skill handles user data via the A2UI protocol. It provides explicit security guidance to mitigate injection risks through the use of boundary markers (---a2ui_JSON---) and mandatory JSON schema validation using the jsonschema library.
  • [External Downloads] (LOW): The documentation references the google-adk and jsonschema Python packages. As these are sourced from trusted organizations and are standard tools for the protocol, they represent no significant security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:47 PM