clean-content-fetch

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs running scripts like scrapling_fetch.py <url> (including examples fetching public sites such as xhslink.com, blogs, news, and WeChat articles) to fetch and convert arbitrary web pages into Markdown for downstream summarization, so it directly ingests untrusted, user-generated third‑party content that can influence subsequent actions.