cincopa

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

• Third-party content exposure detected (high risk: 0.80). The skill issues runtime actions against the public Cincopa API (e.g., "List Assets", "Get Gallery Items", "upload-asset-from-url" and the Membrane "request" proxy) which fetch user-generated/untrusted content from Cincopa that the agent is expected to read and could materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running the Membrane CLI via "npm install -g @membranehq/cli", which fetches and installs remote code that will execute on the host and is a required runtime dependency for the skill.