instagram

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Instagram content (e.g., comments, media, hashtag results) from the open web via the Instagram Graph API — see scripts/api_client.py (get_comments, get_user_media, get_hashtag_recent_media), scripts/comments.py (list/reply), and SKILL.md/ references/graph_api.md — and that content is read and used to drive analysis and actions (analysis, replies, publishing), so untrusted third-party content could indirectly inject instructions.