appmachine

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches and processes data from the external Appmachine service via Membrane CLI commands (e.g., membrane action run --connectionId=... and membrane request CONNECTION_ID /path/to/endpoint in SKILL.md), meaning untrusted third-party/app-generated content can be ingested and influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes the Membrane CLI at runtime (e.g., "npm install -g @membranehq/cli" and "npx @membranehq/cli@latest"), which will fetch and execute remote code from the npm registry (e.g., https://www.npmjs.com/package/@membranehq/cli) and is a required runtime dependency.