UTC

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
Techniques, in order
  1. 1Obtain Capabilities: Generative AIResource Development · AML.T0016.002
  2. 2Develop CapabilitiesResource Development · AML.T0017
  3. 3Stage CapabilitiesResource Development · AML.T0079
  4. 4Drive-by CompromiseInitial Access · AML.T0078
  5. 5AI Agent ClickbaitExecution · AML.T0100
  6. 6LLM Prompt Injection: IndirectExecution · AML.T0051.001
  7. 7AI Agent Tool InvocationPrivilege Escalation · AML.T0053
  8. 8Machine Compromise: Local AI AgentImpact · AML.T0112.000
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.