zoom-automation
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server endpoint at
https://rube.app/mcpto enable functionality. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by processing untrusted data from the Zoom API.
- Ingestion points: Fetches data that may contain user-generated content, such as AI meeting summaries (
ZOOM_GET_A_MEETING_SUMMARY), participant names/lists (ZOOM_GET_PAST_MEETING_PARTICIPANTS), and meeting topics. - Boundary markers: No delimiters or safety instructions are defined to separate Zoom-sourced data from the agent's core instructions.
- Capability inventory: The skill possesses capabilities that could be abused if an injection is successful, including meeting creation (
ZOOM_CREATE_A_MEETING), meeting updates (ZOOM_UPDATE_A_MEETING), and permanent deletion of cloud recordings (ZOOM_DELETE_MEETING_RECORDINGS). - Sanitization: There is no evidence of sanitization or validation of the data retrieved from external Zoom calls before it is used in the agent's context.
Audit Metadata