voodoo-sms

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to run Membrane actions and use "membrane request" to fetch data from the Voodoo SMS API (e.g., messages, contacts) — third-party, user-generated content the agent will read and could use to drive follow-up actions, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires installing and running the Membrane CLI which at runtime fetches and executes remote code via npm/npx (e.g., "npm install -g @membranehq/cli" / "npx @membranehq/cli@latest", which pull from https://registry.npmjs.org/@membranehq/cli), so this external dependency executes remote code and is required by the skill.