userflow

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

• Third-party content exposure detected (medium risk: 0.30). The skill integrates with Userflow via the Membrane CLI, allowing the agent to fetch user-submitted content, records, and messages through API requests and actions.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an external CLI package (@membranehq/cli) from npm, which lacks an explicit registry URL and relies on package-manager resolution without an immutable digest or signature.