a2ui
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference and documentation suite for the A2UI (Agent to UI) protocol version 0.8.
- [SAFE]: It utilizes well-known and trusted external resources, including official Google GitHub repositories for protocol specifications and schemas (e.g., github.com/google/A2UI).
- [SAFE]: No obfuscation, data exfiltration patterns, or malicious persistence mechanisms were identified in the instructions or example code.
- [SAFE]: The documentation explicitly includes security best practices, such as using strict output delimiters (---a2ui_JSON---) and mandatory JSON schema validation to mitigate risks when processing model-generated UI code.
- [SAFE]: Python code snippets provided in the reference guides follow best practices for data parsing and validation, avoiding dangerous functions like eval() or exec().
Audit Metadata