langextract-usage

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Key parameters" section explicitly states text_or_documents accepts a URL string with fetch_urls=True by default, meaning the skill will fetch and process arbitrary public URLs (untrusted third‑party content) as input to lx.extract(), which the agent reads and uses to drive extraction behavior.