instagram

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and acts on public, user-generated Instagram content (e.g., instagram_list_comments, instagram_get_conversation_messages, instagram_get_message, instagram_list_media, instagram_get_user) as shown in Phase 3 (Comment Moderation) and Phase 4 (Direct Messages) of SKILL.md, and that untrusted content is used to decide and drive actions like replies, hides, deletes, and sends—meeting the criteria for indirect prompt injection risk.