Eurostar: Eurostar chatbot security flaws almost left customers exposed to possible security threats

**Eurostar’s AI Chatbot Vulnerabilities Exposed by Security Researchers**

Security researchers at Pen Test Partners uncovered critical flaws in Eurostar’s AI-powered customer support chatbot, which could have enabled malicious exploitation. The vulnerabilities included weak message validation, allowing attackers to manipulate older prompts to execute unauthorized actions—such as extracting system details or potentially exfiltrating data. Additional weaknesses involved unverified conversation IDs and an HTML injection flaw, which permitted JavaScript execution within the chat interface.

Despite the risks, Eurostar confirmed that no customer data was compromised, as the chatbot lacked access to sensitive databases or login-protected information. The company stated that all vulnerabilities have since been mitigated, emphasizing that the chatbot operated in isolation from critical systems.

The discovery highlights broader concerns around rapid AI adoption in enterprises, where misconfigurations and non-human identities are expanding cloud attack surfaces. While Pen Test Partners did not exploit the flaws to access user data, they warned that similar design weaknesses could pose greater risks as chatbot functionality evolves.

The incident underscores the need for rigorous security testing in AI-driven tools, particularly as businesses integrate them into customer-facing operations.

Source: https://www.techradar.com/pro/security/eurostar-chatbot-security-flaws-almost-left-customers-exposed-to-data-theft-and-more

Eurostar cybersecurity rating report: https://www.rankiteo.com/company/eurostar

"id": "EUR1766404527",
"linkid": "eurostar",
"type": "Vulnerability",
"date": "12/2025",
"severity": "25",
"impact": "1",
"explanation": "Attack without any consequences"

{'affected_entities': [{'industry': 'Transportation/Rail',
                        'name': 'Eurostar',
                        'type': 'Company'}],
 'attack_vector': 'AI Chatbot',
 'customer_advisories': 'Eurostar stated that customer data was never at risk '
                        'and vulnerabilities have been addressed.',
 'data_breach': {'data_exfiltration': 'Potential (if chatbot functionality '
                                      'expanded)'},
 'description': 'Pen Test Partners discovered vulnerabilities in Eurostar’s '
                'AI-powered customer support chatbot, including weak '
                'validation and HTML injection flaws. The vulnerabilities '
                'could have allowed malicious prompts to reveal system '
                'information or exfiltrate data, though customer data was not '
                'directly at risk as the chatbot was not connected to customer '
                'databases.',
 'impact': {'brand_reputation_impact': 'Potential reputational damage due to '
                                       'disclosed vulnerabilities',
            'data_compromised': 'None (customer data not at risk)',
            'systems_affected': 'AI-powered customer support chatbot'},
 'investigation_status': 'Vulnerabilities mitigated',
 'lessons_learned': 'Rapid AI adoption can expand cloud attack surfaces and '
                    'introduce vulnerabilities if not properly secured. '
                    'Chatbot integrations must include robust validation and '
                    'access controls to prevent exploitation.',
 'post_incident_analysis': {'corrective_actions': ['Vulnerabilities fixed',
                                                   'Chatbot functionality '
                                                   'reviewed for security'],
                            'root_causes': ['Weak validation of chatbot '
                                            'messages',
                                            'Improper verification of '
                                            'conversation/message IDs',
                                            'HTML injection vulnerability']},
 'recommendations': ['Implement strict validation for all chatbot messages and '
                     'conversation IDs',
                     'Isolate AI systems from sensitive customer databases',
                     'Conduct regular security assessments of AI-powered tools',
                     'Monitor for HTML injection and other common web '
                     'vulnerabilities',
                     'Expand chatbot functionality cautiously with security '
                     'reviews'],
 'references': [{'source': 'TechRadar Pro'},
                {'source': 'Pen Test Partners'},
                {'source': 'City AM'}],
 'response': {'communication_strategy': 'Public statement confirming customer '
                                        'data was never at risk',
              'containment_measures': 'Vulnerabilities mitigated',
              'remediation_measures': 'Vulnerabilities fixed, chatbot '
                                      'functionality reviewed',
              'third_party_assistance': 'Pen Test Partners (vulnerability '
                                        'discovery)'},
 'title': 'Eurostar AI Chatbot Vulnerabilities Discovered',
 'type': 'Vulnerability Exploitation',
 'vulnerability_exploited': ['Weak message validation',
                             'Improper conversation/message ID verification',
                             'HTML injection']}