OpenCode breach exposes users' stored AI provider keys, and some run up charges overnight
A cautionary tale for anyone who stores API keys in a hosted dev tool, plus a twist about AI models refusing to help defenders.
OpenCode, the open-source AI coding agent, said on October 17 that a breach tied to what it called a large-scale distillation attack hit 1.4% of users of OpenCode Console, its hosted service, and that it had emailed those affected. BleepingComputer and TechCrunch report that only users who had linked external providers (Anthropic, OpenAI, Google) were affected, that some reported hundreds to over $1,700 in unauthorized charges, and that Google suspended some projects. Co-founder Dax Raad said the open-source app and CLI were not affected; the company has not said how attackers got in. OpenCode told users to revoke their keys and says refunds are underway. Raad said AI models first refused to help the investigation until it switched to OpenAI's Daybreak cybersecurity model.
On Hacker News, commenters asked why a hosted service held provider keys at all, questioned the unproven 'distillation' label, and argued over earlier warnings about the project's data practices.
-
Knowledge distillation
After exploring Hackers hit AI coding tool OpenCode, running up charges on users’ AI accounts, to understand the "distillation" the company blamed, read Knowledge distillation.
The machine-learning process of transferring knowledge from a large model to a smaller one that is cheaper to run.
Wikipedia · Wade · 5 min
0