linkedin-navigation

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

• Third-party content exposure detected (high risk: 1.00). The skill navigates to and reads live LinkedIn pages (e.g., https://www.linkedin.com/feed/, /messaging/, /notifications/, profiles) using read_page and related browser tools, which exposes the agent to user-generated, public social-media content that could contain indirect prompt injections.