MITRE ATLAStechnique

AML.T0082 RAG Credential Harvesting

Published 2025-09-30 Modified 2025-09-30 Official page ↗
Tactics
Credential Access
Created
2025-09-30

Description

Adversaries may attempt to use their access to a large language model (LLM) on the victim's system to collect credentials. Credentials may be stored in internal documents which can inadvertently be ingested into a RAG database, where they can ultimately be retrieved by an AI agent.

Related

Tactic · MITRE ATLAS (1)

Referenced by MITRE ATLAS · mitigates (2)

  • AML.M0026 Privileged AI Agent Permissions Configuration mitigation
  • AML.M0027 Single-User AI Agent Permissions Configuration mitigation