slack-reply-drafting

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

• Third-party content exposure detected (medium risk: 0.30). In the Slack Reply Drafting workflow, the agent reads outsider-authored free text from Slack channels/DMs/threads via Slack search and message retrieval steps (e.g., slack_search_public_and_private then slack_read_channel/slack_read_thread) and drafts replies from that content.