The Eval Index / Red Teaming & Safety / #159
regaan/basilisk
by regaan · Red Teaming & Safety · updated 1mo ago
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.
49
momentum
84
stars
12
forks
#159
rank
adversarial-aiaiai-red-teamingai-securitybasiliskchatgpt-securitygenetic-algorithmjailbreakllmllm-securityllm-security-compliance-prompt-injectionoffensive-security
View on GitHub →