skills/zoom/skills/zoom-cobrowse-sdk/Gen Agent Trust Hub

zoom-cobrowse-sdk

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or security vulnerabilities were identified within the provided documentation or code snippets.
  • [EXTERNAL_DOWNLOADS]: The skill correctly points to official Zoom domains (zoom.us) and official GitHub repositories (github.com/zoom) for SDK resources and sample code. These references are documented neutrally as they originate from trusted, well-known vendor sources.
  • [CREDENTIALS_UNSAFE]: The skill uses appropriate placeholders for sensitive keys and explicitly warns against exposing the SDK Secret in client-side code, directing users toward secure server-side implementation.
  • [REMOTE_CODE_EXECUTION]: The code examples demonstrate a standard web integration pattern for loading an SDK via CDN. The script injection targets a legitimate Zoom-managed endpoint.
  • [DATA_EXFILTRATION]: There is no evidence of data exfiltration. The documentation includes specific sections on 'piiMask' to help developers protect sensitive user data from being visible to support agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 05:25 PM