AML.T0110: AI Agent Tool Poisoning
Adversaries may achieve persistence by poisoning tools used by AI agents including built-in tools or tools available to the agent via Model Context Protocol (MCP) connections. This involves compromising benign tools already integrated into the agent's environment.
By altering tool behavior such as modifying parameters or descriptions, injecting hidden logic, or redirecting outputs, attackers can maintain long-term influence over the agent's actions, decisions, or external interactions. Poisoned tools may silently exfiltrate data, execute unauthorized commands, or manipulate downstream processes without raising suspicion.
Standards mapping
Where this fits in a TurboPentest engagement
TurboPentest's agentic pentest is powerful and covers a broad range of issues automatically. This particular class is best confirmed in a manual IntegSec engagement, where human pentesters apply deeper methodology and a larger context window than any automated pass.
Frequently asked questions
What is AML.T0110 AI Agent Tool Poisoning?
Adversaries may achieve persistence by poisoning tools used by AI agents including built-in tools or tools available to the agent via Model Context Protocol (MCP) connections. This involves compromising benign tools already integrated into the agent's environment. By altering tool behavior such as modifying parameters or descriptions, injecting hidden logic, or redirecting outputs, attackers can maintain long-term influence over the agent's actions, decisions, or external interactions. Poisoned tools may silently exfiltrate data, execute unauthorized commands, or manipulate downstream processes without raising suspicion.
Which tactics does AML.T0110 belong to?
AML.T0110 maps to the Persistence tactic.
Does TurboPentest test for AI Agent Tool Poisoning?
TurboPentest's agentic pentest is powerful and covers a broad range of issues automatically. This particular class is best confirmed in a manual IntegSec engagement, where human pentesters apply deeper methodology and a larger context window than any automated pass.
Related MITRE ATLAS techniques
- Persistence, AI Attack StagingAML.T0018: Manipulate AI Model
- Resource Development, PersistenceAML.T0020: Poison Training Data
- PersistenceAML.T0061: LLM Prompt Self-Replication
- PersistenceAML.T0070: RAG Poisoning
- PersistenceAML.T0080: AI Agent Context Poisoning
- Persistence, Defense EvasionAML.T0081: Modify AI Agent Configuration
Find these issues before an attacker does
TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.
Start a $99 pentest