AML.CS0043
Malware Prototype with Embedded Prompt Injection
- Type
- Incident
- When
- 2025-06-25
- Actor, as ATLAS names it
- Unknown Threat Actor
- Target
- LLM malware detectors, LLM malware analysis and reverse engineering tools
- Reported by Check Point Research.
Techniques, in order
- 1LLM Prompt CraftingAI Attack Adaptation · AML.T0065
- 2Develop CapabilitiesResource Development · AML.T0017
- 3LLM Prompt Injection: DirectExecution · AML.T0051.000
- 4Evade AI ModelDefense Evasion · AML.T0015
- 5Virtualization/Sandbox EvasionDefense Evasion · AML.T0097
- 6Unsecured CredentialsCredential Access · AML.T0055
- 7Data from Local SystemCollection · AML.T0037
- 8Exfiltration via Cyber MeansExfiltration · AML.T0025
How these attacks work
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.