ConciseSignal

Researchers find ChatGPT flaw enabled cross-account data leaks

Check Point Research discovered a flaw in ChatGPT that allowed an attacker to send a hidden prompt, causing ChatGPT to quietly access data from a victim’s connected Gmail and transfer it to another user’s account. The attacker could exploit the flaw by getting the victim to use a tainted prompt, a shared conversation, or a custom GPT. OpenAI has fixed the underlying issue after disclosure; no user update is needed.

Why it mattersThis incident shows that generative AI tools can be manipulated to access and exfiltrate private user data by abusing internal mechanisms. Organizations using AI integrations should review permissions and monitor for silent data access.

Sources covering this

The Hacker NewsChatGPT Flaw Let a Planted Prompt Send a Victim's Gmail Data to Another Account2:19 PMTechRadarA worrying ChatGPT bug let strangers read Gmail messages via a hidden cross-account channel1:05 PM

In this story

ChatGPTOpenAI
Concise Signal DailyEverything that mattered, every weekday at 7am.

More in AI

18 sources · 2d ago

OpenAI rolls out GPT-6 Astra to most paying users

OpenAI has made its new GPT-6 Astra model available to most paying subscribers a day after its official launch. The rollout, initially described as “messy” by OpenAI’s CEO, now includes ChatGPT Plus, Business, Pro, and Enterprise users, while customers on the lower-priced Go tier do not have access. Astra is also available via the API. OpenAI says the rollout required bringing new systems and additional computing resources online.

9 sources · 11h ago

Anthropic researcher resigns, warns of AI race risks

Jacob Coxon, who worked on AI training at Anthropic and previously OpenAI, resigned this week. He posted that large AI firms are 'gambling with our lives' by pushing towards systems they may not be able to control. Coxon says both companies know the risks but feel locked in a race to develop powerful AI anyway. He called for drastic steps like a pause on new model improvements.

10 sources · 19h ago

OpenAI says AI cracked landmark math problem, faces credit dispute

OpenAI claims its AI has solved a 200-year-old fluid dynamics equation, one of the Clay Millennium math prize problems. The announcement is under fire: NYU mathematician Tristan Buckmaster says OpenAI rushed their work after learning of his progress and tried to sideline other contributors. OpenAI denies accessing rivals’ data, but both sides accuse the other of trying to shape credit. The company spent millions on computing to finish the proof.

5 sources · 21h ago

ChatGPT Images 2.5 adds faster editing tools

OpenAI has updated its ChatGPT Images feature to version 2.5, adding several new editing tools and speeding up image generation. You can now remove backgrounds, resize images to preset dimensions, erase items by brushing over them, and use markup and comment functions directly from a new Edit toolbar. According to TechRadar, the features are available in both web and app versions, though OpenAI hasn't formally announced the rollout yet.