social-push-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and the platform reference files) instructs the agent to use agent-browser to open and inspect public social-media pages (e.g., https://creator.xiaohongshu.com, https://weibo.com, https://mp.weixin.qq.com/) and to run snapshot/eval on those pages to extract element refs and decide clicks/uploads/publishes, so it clearly ingests untrusted, user-generated third‑party content that can influence subsequent actions.