dataforseo

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses ClawLink to call DataforSEO and ingest the returned results (e.g., SERP/on-page/backlinks/business info text) into the agent’s context, which is outsider-authored content from a third-party service rather than the operating user’s own data.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes "npx @useclawlink/cli" at runtime which fetches and executes remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli), and those CLI commands are required for the skill to operate.