jotform

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

• Third-party content exposure detected (medium risk: 0.65). At runtime, the skill uses ClawLink to access the authenticated Jotform account via browser/OAuth and then ingests Jotform form/label/user data (e.g., via actions like jotform_get_user_forms, jotform_get_user_reports, jotform_get_label_resources) into the agent’s LLM context; this is outsider-authored content because it is not authored by the operating user (it’s third-party SaaS data).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run npx @useclawlink/cli commands which fetch and execute remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) at runtime, so this external package is a required runtime dependency that executes remote code.