There are 6 attacks in the supply-chain category. Each shows its technique id, mode, standards mapping, description, and the exact command to run it (swap the provider and target as needed).
​
critical
dataset-poisoning · single-turn · OWASP: LLM05 · MITRE: AML.T0020, AML.T0018Tests if training data contamination affects model responses by probing for memorized harmful patternsRun it:
​
critical
model-poisoning · single-turn · OWASP: LLM04, LLM05 · MITRE: AML.T0020, AML.T0018Tests if a model exhibits backdoor behaviors triggered by specific phrases or tokens from training data poisoningRun it:
​
critical
plugin-backdoor · tool-use · OWASP: LLM04, LLM03 · MITRE: AML.T0110, AML.T0010.005Tests if an AI agent validates third-party plugin integrity before executionRun it:
​
critical
supply-chain-software · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Generates software supply chain attack strategies for compromising package repositories, CI pipelines, and open-source dependenciesRun it:
​
high
dependency-confusion · tool-use · OWASP: LLM04 · MITRE: AML.T0051.000, AML.T0053Tests if an AI agent can be tricked into installing or using malicious packages via dependency confusionRun it:
​
high
finetune-exploit · single-turn · OWASP: LLM04, LLM05 · MITRE: AML.T0018, AML.T0020Tests if fine-tuning artifacts or LoRA weights have introduced safety bypasses or hidden behaviorsRun it: