social-post

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly says "Nếu user chỉ đưa link mà không kèm nội dung, dùng WebFetch để đọc trước," meaning the agent will fetch and read arbitrary user-provided web URLs (untrusted third‑party content) and use that content to inform writing choices, creating a clear avenue for indirect prompt injection.