agent-squad

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow starts heartbeat cron jobs that instruct agents to “Check for assigned work, @mentions, and activity” in the configured task system (e.g., Linear/Trello/GitHub), meaning outsider-authored issue/comment/task text can be ingested at runtime without an additional selection step.