linkedin

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly states it may derive metadata from arbitrary article_url web pages ("Article / Link Posts") and fetch document_url PDFs for posting ("Document and Carousel Posts" / linkedin_create_document_post), meaning it ingests untrusted public web content that can be interpreted and used to build posts and influence subsequent actions.