AML.T0104: Publish Poisoned AI Agent Tool
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 [\[1\]][1]. Tools may also be published as remotely hosted servers [\[2\]][2].
[1]: https://opensourcemalware.com/blog/clawdbot-skills-ganked-your-crypto [2]: https://mcpservers.org/remote-mcp-servers
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.T0104 Publish Poisoned AI Agent Tool?
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 [\[1\]][1]. Tools may also be published as remotely hosted servers [\[2\]][2]. [1]: https://opensourcemalware.com/blog/clawdbot-skills-ganked-your-crypto [2]: https://mcpservers.org/remote-mcp-servers
Which tactics does AML.T0104 belong to?
AML.T0104 maps to the Resource Development tactic.
Does TurboPentest test for Publish Poisoned AI Agent Tool?
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
- Resource DevelopmentAML.T0002: Acquire Public AI Artifacts
- Resource DevelopmentAML.T0008: Acquire Infrastructure
- Resource DevelopmentAML.T0016: Obtain Capabilities
- Resource DevelopmentAML.T0017: Develop Capabilities
- Resource DevelopmentAML.T0019: Publish Poisoned Datasets
- Resource Development, PersistenceAML.T0020: Poison Training Data
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