url-summary

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly fetches and ingests arbitrary public URLs (Step 2: "Fetch Article Content" using the browser tool profile="openclaw", web_fetch, or curl and examples like mp.weixin.qq.com, arxiv.org, blog URLs), so untrusted third‑party page content is read and can directly influence summarization and subsequent actions.