huashu-md-html

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

• Third-party content exposure detected (high risk: 0.85). 能力1/3在运行时会对“外部URL”抓取网页正文（如 scripts/any_to_md.py 的 markitdown.convert(url) 或 scripts/html_to_md.py 的 fetch_url() + trafilatura.extract()），把网页/他人内容转成可读文本写入 md，从而进入后续 LLM 上下文；这是“公共网页内容/他人作者文本”路径。

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)