complain

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow (“complain” skill) passes the user/outside-authored outburst text directly via submit.py standard input (read_message → sanitize_message → post_to_slack) into a Slack webhook submission without an upstream selection step, creating an injection-capable free-text ingestion path.