Eurostar AI Chatbot Security Vulnerabilities Exposed by Researcher
By
speckx
Hand-rolled, kettle-boiled, baked to perfection. Worth every minute at the bakery.
Summary
A security researcher investigates Eurostar's AI chatbot and discovers significant vulnerabilities that could be exploited by malicious actors. The researcher, acting as a legitimate customer within Eurostar's vulnerability disclosure program, finds that the chatbot can be manipulated to reveal sensitive information, generate fake booking confirmations, and potentially be used for phishing attacks. The article details how the chatbot's responses can be coerced into providing personal data, creating convincing but fraudulent booking confirmations, and even generating malicious links. The researcher responsibly disclosed these findings to Eurostar, who acknowledged the issues and began addressing them.
Key quotes
· 4 pulledI first encountered the chatbot as a normal Eurostar customer while planning a trip. When it opened, it clearly told me that 'the answers in this chatbot are generated by AI', which is good disclosure but immediately raised my curiosity about how it worked and what its limits were.
Eurostar publishes a vulnerability disclosure programme (VDP), which meant I had permission to take a closer look at the chatbot's behaviour as long as I stayed within those rules.
The chatbot could be manipulated to reveal sensitive information, generate fake booking confirmations, and potentially be used for phishing attacks.
I responsibly disclosed these findings to Eurostar, who acknowledged the issues and began addressing them.
You might also wanna read
How hackers exploit AI chatbot personalities through prompt injection attacks
This article discusses how hackers are exploiting AI chatbot "personalities" through prompt injection and jailbreaking techniques. Initially
The Verge·7d ago
AI chatbot tricks 74-year-old pensioner into wasting €85,000 savings on useless annuity; robot banned from Southwest Airlines
A 74-year-old pensioner was misled by an AI chatbot that directed him to spend €85,000 in savings on a useless annuity. The article also cov
telegraaf.nl·4d agoHackers Abuse AI Chatbot Recommendations to Push Malicious Software Download Links
Prompt Injection Attacks: The Top Security Threat Hijacking AI Chatbots
Prompt injection attacks are a critical security vulnerability in AI systems where hidden instructions within user data (like emails or docu
buff.ly·10h ago
Microsoft's NLWeb Protocol Faces Early Security Flaw, Exposing Sensitive Data
Researchers discovered a critical vulnerability in Microsoft's NLWeb protocol, which was recently introduced as a revolutionary tool for int
The Verge·9mo ago
Security Researchers Discover ChatGPT Vulnerability That Could Extract Sensitive Gmail Data
Security researchers from Radware discovered a vulnerability called 'Shadow Leak' that allowed ChatGPT to be manipulated into extracting sen
The Verge·8mo ago