Adversarial Ai Python Packages

mitre-atlas-mcp

MITRE ATLAS (adversarial AI) threat landscape MCP. MIT

fas-judgement

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

basilisk-ai

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

ai-flow-architect

Stop trusting single AI outputs. An anti-hallucination framework with dual-brain arbitration, multi-model audit, and evidence chains for LLM quality control.

audison

Stop trusting single AI outputs. An anti-hallucination framework with dual-brain arbitration, multi-model audit, and evidence chains for LLM quality control.

buzur

AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, and more.

vbaf

Vocabulary-Based Adversarial Fuzzing (VB-AF) framework for Large Language Models (LLMs)