mobivate

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 the agent to connect via the Membrane CLI to Mobivate and to run/discover actions (e.g., "membrane action list" and "membrane action run") that will fetch and return Mobivate data such as messages, contacts, templates and reports—user-generated third‑party content the agent is expected to read and act on, which could therefore inject instructions influencing subsequent tool use.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs running the Membrane CLI (e.g., "npm install -g @membranehq/cli@latest" and "npx @membranehq/cli@latest"), which fetches and executes remote code from the npm registry (https://www.npmjs.com/package/@membranehq/cli) at runtime and is required for the skill to operate.