AML.CS0046
Data Destruction via Indirect Prompt Injection Targeting Claude Computer-Use
- Type
- Exercise
- When
- 2024-10-24
- Actor, as ATLAS names it
- Not stated
- Target
- Claude Computer Use Agent
- ATLAS attributes it to HiddenLayer (security evaluation).
Techniques, in order
- 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 2Prompt Infiltration via Public-Facing ApplicationInitial Access · AML.T0093
- 3LLM Prompt Injection: IndirectExecution · AML.T0051.001
- 4LLM JailbreakDefense Evasion · AML.T0054
- 5LLM Prompt ObfuscationDefense Evasion · AML.T0068
- 6AI Agent Tool InvocationExecution · AML.T0053
- 7Data Destruction via AI Agent Tool InvocationImpact · AML.T0101
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.