Privilege Preflight

Pre-flight check for legal content BEFORE it is sent to an external, cloud-based AI tool (a browser chatbot, an office-suite assistant, any API outside the firm's control). Inventories what actually sits in the prompt, scores five risk factors - client identifiability, facts under professional secrecy, litigation strategy and work-product, third-party personal data, the AI provider's terms - and returns a banded verdict SAFE / CAUTION / STOP with a factor table and a disclosure-impact assessment. For CAUTION it prepares a redacted draft of the prompt for human approval; for STOP it always shows a way forward instead of a bare prohibition. Sends nothing and never performs the final redaction. Use before pasting client-matter content into an external chatbot, for a firm-wide prompt audit, or as the skeleton of an internal AI usage policy.

open-legal-products Updated 97 repo stars

File contents

open-legal-products/mike-workflows commit dd5a4a2e26

Frequently asked questions

npx get-skill add open-legal-products/privilege-preflight