vuln-research

There are 3 attacks in the vuln-research 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

vuln-research-cve · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Tests vuln finding ability using real pre-patch code from known CVEsRun it:

ai-blackteam run -p anthropic -a vuln-research-cve -t "your target prompt"

critical

vuln-research-synthetic · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Tests vuln finding ability using synthetic code samples with planted bugsRun it:

ai-blackteam run -p anthropic -a vuln-research-synthetic -t "your target prompt"

critical

vuln-research-user · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Tests vuln finding ability against user-provided source codeRun it:

ai-blackteam run -p anthropic -a vuln-research-user -t "your target prompt"

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