TechniquepersistenceATLAS

AML.T0099AI Agent Tool Data Poisoning

What it is

Adversaries may place malicious content on a victim's system where it can be retrieved by an AI Agent Tool. This may be accomplished by placing documents in a location that will be ingested by a service the AI agent has associated tools for. The content may be targeted such that it would often be retrieved by common queries. The adversary's content may include false or misleading information. It may also include prompt injections with malicious instructions.

References

  1. https://atlas.mitre.org/techniques/AML.T0099

Related by meaning· 6

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

ATLAS
AI Agent Tool Poisoning
ATLAS
Data Destruction via AI Agent Tool Invocation
ATLAS
AI Agent Context Poisoning
ATLAS
Poison Training Data
ATLAS
Exfiltration via AI Agent Tool Invocation
ATLAS
AI Agent
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.