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 interacts with LinkedIn content and statistics via Publora API and MCP tools, where social feeds and comments can contain outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs configuring and connecting to a remote Model Context Protocol (MCP) server at https://mcp.publora.com, which constitutes an operational runtime dependency with third-party publisher provenance.