zoom-team-chat

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests untrusted, user-generated content from Zoom webhooks (e.g., payload.cmd in concepts/webhooks.md and the chatbot handlers in examples/chatbot-setup.md / SKILL.md) and documents LLM-integration patterns (examples/llm-integration.md and the SKILL.md case 'bot_notification') that read/interpret that content to drive actions, so third-party input can influence tool use and decisions.