faceup

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 use Membrane to fetch and proxy data from the FaceUp API (e.g., "membrane action list/run" and "membrane request CONNECTION_ID /path/to/endpoint" against api.faceup.com), which can return untrusted, user-generated content such as Posts/Messages that the agent would read and could influence which actions or parameters it chooses to run.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires and runs the Membrane CLI which is fetched/executed from the npm registry at runtime (commands shown: "npm install -g @membranehq/cli" and "npx @membranehq/cli@latest", i.e. code pulled from https://registry.npmjs.org/@membranehq/cli), so remote code is downloaded and executed as a required dependency.