crowdin

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow uses ClawLink to interact with Crowdin (e.g., listing actions, describing inputs, and running actions), which necessarily involves fetching and ingesting Crowdin project content authored by other users (Crowdin contributors) into the agent’s LLM context via the CLI/API responses.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs npx @useclawlink/cli during runtime which fetches and executes remote npm package code (https://www.npmjs.com/package/@useclawlink/cli), so an external package is required at runtime and can execute code/control agent actions.