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"
- ATLAS attributes it to Cybernews Investigation Team (security evaluation).
Techniques, in order
- 1Acquire InfrastructureResource Development · AML.T0008
- 2LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 3AI-Enabled Product or ServiceAI Model Access · AML.T0047
- 4Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
- 5LLM Prompt Injection: DirectExecution · AML.T0051.000
- 6User ExecutionExecution · AML.T0011
- 7Command and Scripting InterpreterExecution · AML.T0050
- 8Steal Web Session CookieCredential Access · AML.T0113
- 9LLM Response RenderingExfiltration · AML.T0077
- 10Use Alternate Authentication Material: Web Session CookieLateral Movement · AML.T0091.001
- 11External HarmsImpact · AML.T0048
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.