facebook-messenger

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs connecting to Facebook Messenger and running actions or proxying arbitrary Facebook API endpoints (e.g., "npx @membranehq/cli ... action run" and the "request CONNECTION_ID /path/to/endpoint" / "You can also pass a full URL" lines), which exposes untrusted, user-generated Messenger content and third-party pages that the agent would read/interpret and could materially influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running "npx @membranehq/cli@latest" at runtime, which fetches and executes remote code from the npm registry (e.g., https://registry.npmjs.org/@membranehq/cli), so external content is executed and is a required dependency.