Vulnerability in Anthropic's Claude AI
A security researcher has discovered a critical flaw in Anthropic's Claude AI, allowing attackers to steal user data by exploiting the platform's own File API.
The vulnerability enables attackers to use hidden commands to hijack Claude's Code Interpreter, tricking the AI into sending sensitive data, such as chat histories, directly to the attacker.
Anthropic initially dismissed the report on October 25 but later acknowledged a "process hiccup" on October 30.
The exploit involves a chained attack that abuses the platform's own API, highlighting the need for robust security measures in AI systems.
Author's summary: Claude AI has a critical vulnerability.More News
- Hitachi hunting ideas
- Standard Chartered S’pore 6-Month Fixed Deposit Promo Offers Up To 1.15% p.a. from 4 Nov 2025
- EIB agrees €500m green loan for Iberdrola’s Windanker project
- Uganda: Kasese Attack Death Toll Hits 19 As Arrests Reach 40
- How many searches does it take to change a lightbulb - Ireland's DIY embarrassment revealed
- John Lewis Christmas advert music Where Loves Lives to become charity single
- Botswana's Critical Transition: From Parental Provider to Democratic Enabler
- John Lewis 2025 Christmas advert stars classic '90s house banger
- John Lewis unveils tear-jerking Christmas advert set to iconic 90s club classic
- All's Fair: What to know about Kim Kardashian's new show as first reviews come in