AML.CS0055
AI ClickFix: Hijacking Computer-Use Agents Using ClickFix
- Type
- Exercise
- When
- 2025-05-24
- Actor, as ATLAS names it
- Not stated
- Target
- Claude Computer-Use Agent
- ATLAS attributes it to Embrace the Red (security evaluation).
Techniques, in order
- 1Obtain Capabilities: Generative AIResource Development · AML.T0016.002
- 2Develop CapabilitiesResource Development · AML.T0017
- 3Stage CapabilitiesResource Development · AML.T0079
- 4Drive-by CompromiseInitial Access · AML.T0078
- 5AI Agent ClickbaitExecution · AML.T0100
- 6LLM Prompt Injection: IndirectExecution · AML.T0051.001
- 7AI Agent Tool InvocationPrivilege Escalation · AML.T0053
- 8Machine Compromise: Local AI AgentImpact · AML.T0112.000
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.