Vercel Breached via Third-Party AI Tool, User Keys at Risk

Vercel disclosed a security breach after an attacker compromised an employee’s third-party AI tool, then used that foothold to access a limited set of customer API keys and credentials stored on the platform.

What's the Scoop?

• How it happened: The attack started through Context.ai, an enterprise AI platform used by a Vercel employee. The attacker used that access to take over the employee's Google Workspace account, then worked deeper into Vercel's internal systems. Vercel CEO Guillermo Rauch described the group as "highly sophisticated" and suspects the operation was "significantly accelerated by AI."
• What was accessed: Some credentials — API keys, database passwords, etc. — that Vercel lets developers store on their platform were exposed. Credentials flagged as "sensitive" by developers were protected and unreadable even to the attacker. Only the non-sensitive ones were at risk.
• What Vercel has done: Vercel is working with Google's Mandiant team, additional cybersecurity firms, and law enforcement. Next.js, Turbopack, and Vercel's other open source projects were not affected. New credential management tools have already been shipped to the dashboard.
• What customers should do: Any credential stored in Vercel that wasn't flagged as sensitive should be treated as compromised and replaced  - meaning go to the originating service and issue a new key entirely.