Eurostar Chatbot Security Flaws Nearly Exposed Customers to Possible Security Threats


  • Pen Test Partners discovered flaws in Eurostar’s AI chatbot, including weak validation and HTML injection.
  • Eurostar says customer data was never at risk; the vulnerabilities have since been mitigated
  • Palo Alto warns that rapid adoption of AI expands cloud attack surfaces via misconfigurations and non-human identities

Eurostar’s recently introduced AI-based customer support chatbot was riddled with cybersecurity vulnerabilities that opened the door to a host of potential risks, experts have warned.

Pen Test Partners researchers found that the chatbot correctly validated only the most recent messages in a conversation, meaning older messages could be edited to contain a malicious prompt. This prompt can be virtually anything, from revealing system information to (possibly) exfiltrating sensitive customer data.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top