Record summary
A quick snapshot of what this page covers.
Techniques9Attack methods in this attacker goal.
ATT&CKTA0003Related cybersecurity reference, if available.
DatasetATLASMain public source for this page.
Tactic overview
What attackers may be trying to achieve.
- ATLAS ID
- AML.TA0006
- ATT&CK external ID
- TA0003
- Technique count
- 9
Technique coverage
Attack methods grouped under this attacker goal.
AML.T0080 - AI Agent Context Poisoning
demonstrated
AML.T0099 - AI Agent Tool Data Poisoning
feasible
AML.T0110 - AI Agent Tool Poisoning
realized
AML.T0061 - LLM Prompt Self-Replication
demonstrated
AML.T0018 - Manipulate AI Model
realized
AML.T0081 - Modify AI Agent Configuration
demonstrated
AML.T0020 - Poison Training Data
realized
AML.T0093 - Prompt Infiltration via Public-Facing Application
demonstrated
AML.T0070 - RAG Poisoning
demonstrated
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.