Garak Python Packages

pyatr

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.

veldt-kya

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

llama-stack-provider-trustyai-garak

Out-Of-Tree Llama Stack Eval Provider for Red Teaming LLM Systems with Garak

llm-security-gates

Python security gates for LLM systems: prompt-injection filtering, model artifact scanning, and garak-based red-team scoring.

garak-multilingual

Turkish + multilingual prompt-injection, jailbreak & casefold-evasion probes for NVIDIA garak — test your LLM's non-English attack surface. OWASP LLM Top 10 / MITRE ATLAS mapped.