Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions

Tego AI disclosed research showing that Anthropic’s Claude Tag Slack integration can be triggered by literal "@Claude" text and untrusted automated messages, potentially allowing the agent to perform unauthorized enterprise actions (data retrieval, publication, deletion); Tego AI demonstrates impact, recommends least-privilege connections, runtime authorization, and logging, and reported the findings to Anthropic, which classified the submission as informative and disputed the default triggering behavior.