Skip to content
Thoughts on AIT019

Your OpenAI, Claude or Gemini API Key Compromised? Here's What to Do

T019 · by — AI Strategist, Practitioner & Educator · Founder, AI Center of Excellence

A follow-up to the OpenCode breach: what to do when any product holding your OpenAI, Claude or Gemini API keys is hacked. Alexey's three steps: revoke the keys at the provider (all of them if you a...

Full Explanation

A follow-up to the OpenCode breach: what to do when any product holding your OpenAI, Claude or Gemini API keys is hacked. Alexey's three steps: revoke the keys at the provider (all of them if you are not sure which ones you gave), put a spend limit you can afford to lose on the new keys, and give keys only to services whose security team you trust, because such services are targets for distillation attacks.

---

Transcript

Read every word ↓

What to do if you wake up and understand that the company to which you gave your API keys from your AI providers has been a target of the hack. For instance, today, it happened with OpenCode, but it may happen with any company which is having your API keys. First of all, log in to the provider of your model, to Google, to OpenAI, to Anthropic, and revoke the API keys which you have given to this other product which has been hacked. If you don't remember which API keys you have given to this product, just revoke all the API keys.

Second one, set up the limits to the reissued API keys. It can be $20. It can be $100, but just some amount which you are ready to lose if something bad happens. And third, always choose really well the companies or the services which are asking your API keys from Anthropic, OpenAI, Google, or other frontier companies because they can be a target of some distillation attacks, and you just want to be sure that the security team which is working on these products is strong enough to prevent such attacks.

Newsletter

Found this useful?

Join the newsletter. You get one e-mail when something new and useful is out: a video, a guide, a tool. No spam, no schedule, and you can leave with one click.

Alexey Makarov

Alexey Makarov

AI Strategist, Practitioner & Educator. Founder & Global Lead of the AI Center of Excellence at SEFE. Creator of the Unreasonable AI YouTube channel. Based in Berlin.

About Alexey →