wechat-tech-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web searches and fetches/scrapes external articles (Step 2/Step 3 in SKILL.md: "使用 WebSearch" and "使用 WebFetch 获取2-5篇代表性文章" including sources like 掘金、CSDN、Medium、GitHub README) and the generator also accepts a reference URL (--url) that the agent is instructed to read and incorporate, so it ingests untrusted public third‑party content as part of its workflow.