zoom-automation

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from Zoom meeting content which could contain malicious instructions.
  • Ingestion points: ZOOM_GET_PAST_MEETING_PARTICIPANTS and ZOOM_GET_A_MEETING_SUMMARY (in SKILL.md) process external participant data and AI-generated summaries.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill possesses high-privilege capabilities including meeting creation (ZOOM_CREATE_A_MEETING), deletion of recordings (ZOOM_DELETE_MEETING_RECORDINGS), and webinar registration management (ZOOM_ADD_A_WEBINAR_REGISTRANT).
  • Sanitization: No sanitization or validation of the ingested external content is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint (https://rube.app/mcp) to provide the necessary tool suite.
  • [SAFE]: No obfuscated code, hardcoded credentials, or persistence mechanisms were detected within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 07:16 AM