linkedin-analytics

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow integrates a social media analytics and engagement tool (Publora) that reads LinkedIn posts, comments, and metrics where external users can post comments and content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install an external MCP server via HTTP transport from publora.com, which constitutes an inbound operational runtime dependency from a third-party publisher.