uservoice

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md instructs the agent to use the Membrane CLI to connect to UserVoice and run actions against UserVoice data (e.g., Suggestions, Comments, Forums) — clearly ingesting and acting on untrusted, user-generated third‑party content as part of its workflow (see "UserVoice Overview" and "Working with UserVoice" / "Running 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@latest" / "npx @membranehq/cli@latest"), which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@membranehq/cli) at runtime, so it is a required runtime dependency that can execute remote code.