n8n-agents

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

• Third-party content exposure detected (high risk: 0.85). The required runtime path is a chat-triggered agent where outsider-authored free text (e.g., Slack message content from other users) is passed as chatInput/text into the Agent node (text: '={{ $json.userMessage }}' / chatInput: '={{ $('Slack Trigger').item.json.text }}'), which the agent then includes in the LLM context.