skills/zoom/skills/contact-center/ios/Gen Agent Trust Hub

contact-center/ios

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation and implementation patterns for the Zoom Contact Center SDK. All external links point to official Zoom domains, which are recognized as vendor resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for configuration data required by the SDK.
  • Ingestion points: The skill handles data such as userName, entryId, and apiKey through the ZoomCCContext and ZoomCCItem objects in examples/service-patterns.md.
  • Boundary markers: The documentation does not explicitly specify the use of delimiters for these inputs.
  • Capability inventory: The SDK facilitates communication services including chat, video, and scheduled callbacks.
  • Sanitization: Input validation or sanitization is not explicitly detailed in the provided integration snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:55 PM
Security Audit — agent-trust-hub — contact-center/ios