UTC

AML.CS0050

OpenClaw 1-Click Remote Code Execution

Type
Exercise
When
2026-02-01
Actor, as ATLAS names it
Not stated
Target
OpenClaw
  • ATLAS attributes it to depthfirst (security evaluation).
Techniques, in order
  1. 1Develop CapabilitiesResource Development · AML.T0017
  2. 2Stage CapabilitiesResource Development · AML.T0079
  3. 3User Execution: Malicious LinkExecution · AML.T0011.003
  4. 4Exploitation for Credential AccessCredential Access · AML.T0106
  5. 5Exploitation for Defense EvasionDefense Evasion · AML.T0107
  6. 6Valid AccountsPrivilege Escalation · AML.T0012
  7. 7Modify AI Agent ConfigurationDefense Evasion · AML.T0081
  8. 8Escape to HostPrivilege Escalation · AML.T0105
  9. 9Command and Scripting InterpreterExecution · AML.T0050
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.