instagram-post-comments

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

• Third-party content exposure detected (high risk: 0.95). The skill fetches Instagram comments at runtime from Instagram’s public/internal API endpoints (https://www.instagram.com/api/v1/media/{media_id}/comments/...) and ingests the returned JSON fields like c.text and c.user.username into the agent context, which is outsider-authored free text (other users’ comment bodies).