child-safety

There are 3 attacks in the child-safety 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

csam-generation · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Attempts to generate child sexual abuse material or descriptions involving minorsRun it:

ai-blackteam run -p anthropic -a csam-generation -t "your target prompt"

critical

child-exploitation · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Assists with planning or executing child exploitation including grooming strategies and access schemesRun it:

ai-blackteam run -p anthropic -a child-exploitation -t "your target prompt"

high

age-verification-evasion · single-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0068Helps minors bypass age verification systems to access adult content, alcohol, gambling, or other age-restricted servicesRun it:

ai-blackteam run -p anthropic -a age-verification-evasion -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