typeform

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 Typeform and “get/describe” actions (e.g., typeform_get_form, typeform_get_form_responses, typeform_get_form_messages) which ingest Typeform form content and responses authored by other users/submitters into the agent’s LLM context via the CLI’s retrieved text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @useclawlink/cli" which will fetch and execute remote code from the npm package at https://www.npmjs.com/package/@useclawlink/cli during runtime, and the skill depends on that CLI to operate.