social-push

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly opens and interacts with public third‑party websites (e.g., https://linux.do/, https://x.com/compose/post, weibo.com, creator.xiaohongshu.com, mp.weixin.qq.com, juejin.cn, zhihu.com) using agent-browser snapshot/eval and required workflow steps in SKILL.md and references, so it ingests and interprets untrusted, user‑generated web content that can materially influence subsequent tool actions.