AI & LLM Security
AI & LLM Security is the set of tools used to find and reduce security risks in generative AI models, LLM applications, and AI agents. It covers authorized red teaming of models and agents, prompt-injection and jailbreak testing, and runtime guardrails that watch agent behavior. Tools here protect the AI systems themselves, rather than using AI to test other software.

iFixAi
iFixAi is a freemium open-source auditor used to test AI agents in a simulation of their business for security, engineering, and assurance teams.
AI & LLM SecurityFreemiumOpen source
Snyk Agent Scan
Snyk Agent Scan is a free open-source CLI used to discover and scan AI agents, MCP servers, and agent skills for security and engineering teams.
AI & LLM SecurityFreeOpen source
NVIDIA OpenShell
OpenShell is a free open-source runtime used to sandbox autonomous AI agents under declared access policies for security and platform teams.
AI & LLM SecurityFreeOpen source
BLA (Blind LLM Agents)
BLA (Blind LLM Agents) is a free open-source CLI and MCP server used to protect release artifacts from AI reverse-engineering agents for software authors.
Sapper
Sapper is an open-source multi-agent pentest orchestrator where an AI commander directs worker agents that use Kali tools in authorized labs and CTFs.

Ultrafuzz
Ultrafuzz is an open-source orchestrator from the Monad Foundation that runs AI agents to fuzz Solidity smart contracts, hunt threats, and report findings.

SkillSpector
SkillSpector is an open-source security scanner used to check AI agent skills for prompt injection, data exfiltration, and supply chain risks for developers.
AI & LLM SecurityFreeOpen source
NeMo Guardrails
NeMo Guardrails is a free open-source NVIDIA toolkit used to add programmable safety rails to LLM chat apps for AI engineers and security teams.
AI & LLM SecurityFreeOpen source
PyRIT
PyRIT is a free open-source AI red-teaming framework used to identify risks in generative AI systems for security professionals and engineers.
AI & LLM SecurityFreeOpen source
Promptfoo
Promptfoo is a freemium open-source CLI and library used to evaluate and red-team LLM applications and agents for developers and security teams.
AI & LLM SecurityFreemiumOpen sourcegarak
garak is a free open-source LLM vulnerability scanner used to probe language models for security weaknesses during authorized red-team tests.
AI & LLM SecurityFreeOpen source
Verno Labs
Verno Labs is a paid AI agent security platform used to red-team and monitor AI agents you are authorized to test, built for enterprise security teams.
AI & LLM SecurityPaid