slack

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

• Third-party content exposure detected (high risk: 0.90). This skill uses the Membrane CLI to fetch Slack workspace data (e.g., actions like get-conversation-history and search-messages) which are user-generated, untrusted third-party messages/files that the agent is expected to read and could materially influence subsequent actions such as posting or updating messages.