pubnub

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using "membrane action run" and "membrane request" to fetch data from the PubNub API (a public third-party messaging platform that carries user-generated messages/files), so the agent will ingest and act on untrusted third‑party content returned from PubNub.

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 third‑party Membrane CLI via "npm install -g @membranehq/cli" (fetched from the npm registry, e.g. https://registry.npmjs.org/@membranehq/cli), which downloads and executes remote code at runtime and is a required dependency for the skill.