MITRE ATLAS · Credential Access
AML.T0083 · Credentials from AI Agent Configuration
Adversaries may access the credentials of other tools or services on a system from the configuration of an AI agent.
Detections 1
Related techniques
- ASI03 Identity and Privilege Abuse OWASP Agentic
In the news
-
ARTEX: How Cybercriminals Use AI Agents to Scale Their Attacks
Amazon reports criminals running offensive campaigns with ARTEX, an open-source agentic AI pentesting framework, including credential theft and deepfake ID bypass tests.
HuntHunt for ARTEX agent requests to LLM-style API endpoints in proxy and API gateway logs
-
Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys
Amazon threat intelligence observed attacker AI agents hunting internet-exposed AI apps like LiteLLM, One API and Dify to steal stored AI provider API keys.
HuntHunt for unusual AI provider API key use and probing of exposed LiteLLM, One API and Dify instances
Tools
Detect or mitigate it
- Weir Agent & MCP security · Assess
CVEs
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.