linkedin-content

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research Methodology and Quality Standards explicitly require using WebSearch to fetch "viral LinkedIn posts" and current LinkedIn algorithm priorities (public, user-generated web content) which the agent is expected to read and incorporate into its posting strategy, creating clear exposure to untrusted third-party content.