Techniquecredential-accessATLAS

AML.T0082RAG Credential Harvesting

What it is

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.

References

  1. https://atlas.mitre.org/techniques/AML.T0082

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS
AI Agent Tool Credential Harvesting
ATLAS
False RAG Entry Injection
ATLAS
Gather RAG-Indexed Targets
ATLAS
RAG Poisoning
ATLAS
Data from AI Services
ATLAS
Retrieval Content Crafting
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.