skills/glebis/claude-skills/zoom/Gen Agent Trust Hub

zoom

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script executes a system command to automatically detect the user's timezone.
  • Evidence: In scripts/zoom_meetings.py, subprocess.run is used to call readlink /etc/localtime. This is a benign operation used to ensure Zoom meetings are scheduled with the correct local time offset.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes meeting data and recordings from the Zoom API, which is a standard data ingestion surface.
  • Ingestion points: Meeting topics, agendas, and transcripts are retrieved via the Zoom API in scripts/zoom_meetings.py.
  • Boundary markers: The skill presents meeting data to the agent in Markdown or JSON format without explicit delimiters to separate external content from instructions.
  • Capability inventory: The skill allows the agent to create, update, and delete meetings based on these inputs.
  • Sanitization: Data is retrieved directly from Zoom and passed to the agent's context without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:42 AM