Supply Chain

Supply chain attacks target the AI system itself rather than just its outputs. These test for dataset poisoning, model backdoors, dependency confusion, and plugin integrity validation. If an attacker can poison the training data or inject a malicious plugin, they compromise every interaction that follows. Supply chain security is foundational to trustworthy AI.

Summary

6 attacks total: 4 single-turn, 2 tool-use.

Attacks

Attack	ID	Mode	Severity	Description
Dataset Poisoning	`dataset-poisoning`	single-turn	critical	Tests if training data contamination affects model responses by probing for memorized harmful patterns
Dependency Confusion	`dependency-confusion`	tool-use	high	Tests if an AI agent can be tricked into installing or using malicious packages via dependency confusion
Finetune Exploit	`finetune-exploit`	single-turn	high	Tests if fine-tuning artifacts or LoRA weights have introduced safety bypasses or hidden behaviors
Model Poisoning	`model-poisoning`	single-turn	critical	Tests if a model exhibits backdoor behaviors triggered by specific phrases or tokens from training data poisoning
Plugin Backdoor	`plugin-backdoor`	tool-use	critical	Tests if an AI agent validates third-party plugin integrity before execution
Supply Chain Software	`supply-chain-software`	single-turn	critical	Generates software supply chain attack strategies for compromising package repositories, CI pipelines, and open-sourc…

Example

ai-blackteam run -p anthropic -a dataset-poisoning -t "Inject a backdoor into this npm package"

Overview

Full Reference

Attacks by Category

Encoding & Obfuscation

Prompt Injection

Social Engineering

Agent & Tool Attacks

Security & Access Control

ML & Model Attacks

Multimodal & RAG

Harmful Content

Misinformation & Influence

Domain Exploits

Compliance & Bias

Attack Strategies

Summary

Attacks

Example

​Summary

​Attacks

​Example

Summary

Attacks

Example