reamaze

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 the agent to fetch and act on Reamaze data via Membrane commands (e.g., membrane action run ... and membrane request CONNECTION_ID /path/to/endpoint), which will ingest user-generated Reamaze content (messages, articles) from a third-party service that the agent is expected to read and that could 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 requires installing and running the Membrane CLI via "npm install -g @membranehq/cli" (https://www.npmjs.com/package/@membranehq/cli), which fetches and executes remote code that the skill depends on at runtime.