squad-run

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow injects outsider-authored free text from API-fetched task fields (e.g., /task/$ID → title,description,spec,plan_review_comments,implementation_notes,decision_log,review_comments) into the agents’ LLM prompts via template placeholder filling and Task(prompt=<filled template content>), so any such fields authored by other users can reach the LLM context (indirect prompt injection risk).