Unsecured Credentials
Description
Adversaries may search compromised systems to find and obtain insecurely stored credentials.
These credentials can be stored and/or misplaced in many locations on a system, including plaintext files (e.g. bash history), environment variables, operating system, or application-specific repositories (e.g. Credentials in Registry), or other specialized files/artifacts (e.g. private keys).
- ATLAS ID
- AML.T0055
- Maturity
- RealizedUsed by real adversaries against AI systems in the wild.
- Platforms
- Enterprise
Mitigations
ATLAS 2026.09 lists no mitigation for this technique.
Case studies that use it
- AML.CS0016Achieving Code Execution in MathGPT via Prompt Injection
- AML.CS0023ShadowRay: Hijacking Exposed Ray Clusters
- AML.CS0027Organization Confusion on Hugging Face
- AML.CS0030LLM Jacking
- AML.CS0043Malware Prototype with Embedded Prompt Injection
- AML.CS0047Code to Deploy Destructive AI Agent Discovered in Amazon Q VS Code Extension
- AML.CS0054Data Exfiltration via Remote Poisoned MCP Tool
- AML.CS0068Autonomous OpenAI Evaluation Agents Compromise Hugging Face Infrastructure
- AML.CS0069GTG-1002 Claude Code Espionage Campaign
Related ATT&CK technique
ATLAS adapts this technique from MITRE ATT&CK Enterprise.
Across MITRE's defensive frameworks
Linked through the 1 ATT&CK technique above.
Counter with D3FEND
Defensive techniques MITRE D3FEND maps to the same ATT&CK techniques.
- D3-NTPMNetwork Traffic Policy Mapping1 shared
- D3-ANCIAuthentication Cache Invalidation1 shared
- D3-CCSACredential Compromise Scope Analysis1 shared
- D3-CHCredential Hardening1 shared
- D3-CRCredential Revocation1 shared
- D3-CROCredential Rotation1 shared
- D3-CTSCredential Transmission Scoping1 shared
- D3-DUCDecoy User Credential1 shared
- D3-MFAMulti-factor Authentication1 shared
- D3-RICReissue Credential1 shared
- D3-SCPSystem Configuration Permissions1 shared
- D3-AMAccess Modeling1 shared
Detect with CAR
MITRE CAR analytics that cover the same ATT&CK techniques.