clickup

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads external task data, comments, and project records from ClickUp via Membrane actions and API requests, exposing the agent to outsider-submitted content such as task descriptions and comments.

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 and run the Membrane CLI package from npm (@membranehq/cli), which relies on a third-party registry service without an enforced immutable digest or cryptographic proof of provenance, placing it in the medium risk tier for common/reputable unofficial operational dependencies.