share-with-tracking

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors reader activity, questions, and comments submitted by external users viewing shared links, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to install and configure an external MCP server from artifactsend.com via shell commands, representing an unverified third-party operational dependency.