scrapling-article-fetch

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests arbitrary public webpages (e.g., user-supplied URLs like mp.weixin.qq.com) via scripts/scrapling_fetch.py (Fetcher.get(url)) and then automatically parses that untrusted, user-generated content into Markdown and acts on it (writing to Feishu via scripts/md_to_feishu_doc.py) as described in SKILL.md, so third-party page content could indirectly inject instructions that influence the agent's behavior.