zoom-automation

Warn

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires registering an external MCP server at https://rube.app/mcp to function. This endpoint provides the tool schemas and execution logic for the Zoom integration and originates from a source that is not a recognized trusted vendor or well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external Zoom API responses, which could contain untrusted instructions from meeting participants or generated summaries.
  • Ingestion points: External data enters the context through tools such as ZOOM_GET_A_MEETING_SUMMARY and ZOOM_GET_PAST_MEETING_PARTICIPANTS (documented in SKILL.md).
  • Boundary markers: There are no specified boundary markers or instructions to the agent to ignore embedded content within the retrieved Zoom data.
  • Capability inventory: The agent has capabilities to modify or delete Zoom recordings and meetings (e.g., ZOOM_DELETE_MEETING_RECORDINGS).
  • Sanitization: The skill does not mention any sanitization or validation processes for the incoming external data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 10, 2026, 10:16 AM
Security Audit — agent-trust-hub — zoom-automation