UTC

AML.CS0060

Cross-Site Scripting via Prompt Manipulation in Lenovo AI Chatbot

Type
Exercise
When
2025-08-18
Actor, as ATLAS names it
Not stated
Target
Lenovo AI chatbot, "Lena"
Techniques, in order
  1. 1Acquire InfrastructureResource Development · AML.T0008
  2. 2LLM Prompt CraftingAI Attack Adaptation · AML.T0065
  3. 3AI-Enabled Product or ServiceAI Model Access · AML.T0047
  4. 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
  5. 5LLM Prompt Injection: DirectExecution · AML.T0051.000
  6. 6User ExecutionExecution · AML.T0011
  7. 7Command and Scripting InterpreterExecution · AML.T0050
  8. 8Steal Web Session CookieCredential Access · AML.T0113
  9. 9LLM Response RenderingExfiltration · AML.T0077
  10. 10Use Alternate Authentication Material: Web Session CookieLateral Movement · AML.T0091.001
  11. 11External HarmsImpact · AML.T0048
The full case study on MITRE ATLAS →

From MITRE ATLAS 2026.10 (Apache-2.0). ShieldMap lists who and what was involved and the techniques used, and links to ATLAS for the write-up; it does not copy the steps. Attribution is ATLAS's, not ShieldPi's.