zyte-api

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to call Zyte API actions (e.g., “extract data from a URL”), which at runtime can ingest free-form page/body text fetched from arbitrary URLs supplied by the operating user—an outsider-authored source—into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill requires running npx @useclawlink/cli which at runtime fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and uses ClawLink (https://claw-link.dev) to deliver action definitions that can directly control agent prompts/behavior.