Security Vulnerability in Gemini 2.5 Pro

Gemini API
,
1

I am a security researcher and during my experiments I found a vulnerability in Gemini 2.5 Pro.

It has been fixed on Gemini 3 (I tested it for comparison), but it results in a successful jailbreak roughly 50% of the time in Gemini 2.5 Pro, which as far as I know is available to old users and in other AI aggregators such as OpenRouter (which is where I tested it).

Basically if you use a fake markup you convince the model to output NSFW sexually explicit content, or exfiltrate a secret string from the system prompt (capture-the-flag style).

More details here: https://drive.google.com/file/d/1eQMf48oZcCSYS0oBKwC3V-59p6hSJ-AT/view?usp=sharing

I tried sending to the Google Bug Bounty as it is security related, but it says it’s out of scope, so I’m reporting here instead as an alternative so that it reaches Gemini team and they decide the best course of action.

2

Hello, can you still use Gemini 2.5 pro so far?

3

Hi, I can but just if I use it through OpenRouter. When I created my Google Cloud account, it said that Gemini 2.5 Pro isn’t available to new users. Maybe if your Google Cloud account is older than mine you will still be able to use it from Google’s API?

4

Thanks for explaining! I registered as a Pro user in 2025, yet I can’t access 2.5 Pro on AIStudio now​:face_holding_back_tears: