virtual-agent
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official Zoom sample repositories on GitHub for Android and iOS implementations. These are recognized vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill describes the integration of a conversational virtual agent, which by design processes untrusted user input. 1. Ingestion points: User input captured via web chat or mobile bridge. 2. Boundary markers: Not specified in the guidelines. 3. Capability inventory: Supports bridge callbacks and URL navigation. 4. Sanitization: Relies on the host application and SDK implementation.
Audit Metadata