zoom-mcp/whiteboard

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Zoom Whiteboards, which could contain untrusted instructions intended to influence agent behavior.
  • Ingestion points: Tools such as get_a_whiteboard and list_whiteboards fetch content from the Zoom service (SKILL.md, references/tools.md).
  • Boundary markers: The instructions lack delimiters or warnings to ignore instructions embedded within the retrieved whiteboard content.
  • Capability inventory: The skill includes tools for managing whiteboard collaborators, such as add_a_whiteboard_collaborator and delete_a_whiteboard_collaborator, which could be abused if the agent is influenced by malicious content (SKILL.md, references/tools.md).
  • Sanitization: There are no guidelines provided for sanitizing or validating the content retrieved from whiteboards before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:55 PM
Security Audit — agent-trust-hub — zoom-mcp/whiteboard