npm

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Proxy requests" and action/run workflow (SKILL.md) explicitly instructs sending requests through Membrane to the public Npm API (e.g., via membrane request CONNECTION_ID /path/to/endpoint and action/list/run against a Npm connection), which ingests untrusted, user-generated package/README/registry data that the agent is expected to read and act on.