Skills
Navigate
skills/zoom/skills/zoom-mcp/tasks/Gen Agent Trust Hub

zoom-mcp/tasks

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as documentation for the Zoom Tasks interface. All external URLs, such as the streaming endpoint and developer documentation, reside on official vendor-owned domains (zoom.us).
  • [NO_CODE]: No executable scripts, binaries, or automated installation commands are included. The skill consists entirely of markdown documentation and tool scope definitions.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines tools that process external content, which is a standard characteristic of task management interfaces.
  • Ingestion points: get_task_detail and get_a_task_comments in references/tools.md read user-generated data.
  • Boundary markers: No specific boundary markers are defined in the guidance for separating task data from instructions.
  • Capability inventory: The skill includes capabilities to modify or delete data, such as trash_task and delete_task_comment in references/tools.md.
  • Sanitization: Not applicable for this documentation-only skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:55 PM
Security Audit — agent-trust-hub — zoom-mcp/tasks