Esc
There are no artifacts defined on this offensive technique (yet). Please consider contributing an addition to D3FEND.
Publish Poisoned AI Agent Tool - AML.T0104
(ATLAS Technique)
Definition
Adversaries may create and publish poisoned AI agent tools. Poisoned tools may contain an LLM Prompt Injection, which can lead to a variety of impacts.
Tools may be published to open source version control repositories (e.g. GitHub, GitLab), to package registries (e.g. npm), or to repositories specifically designed for sharing tools (e.g. OpenClaw Hub). These registries may be largely unregulated and may contain many poisoned tools [[opensourcemalware]]. Tools may also be published as remotely hosted servers [[mcpservers]].
D3FEND Inferred Relationships
There are no artifacts defined on this offensive technique (yet). Please consider contributing an addition to D3FEND.