ic-feedback

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

• Third-party content exposure detected (high risk: 0.95). The skill’s required operator workflow reads outsider-authored free text from the public feedback queue (e.g., message, expected, got, category) via ic_admin_list_feedback / GET /api/agent/feedback/pending / GET /api/agent/feedback/{ticket_id}, which the doc states “enters YOUR LLM context.”