Products Index

Vendor tools, platforms, agentic-AI products, model offerings, security-tooling integrations.

Pages

• ADR-Bench — A defender-side benchmark for detecting attacks against AI agents that operate through the Model Context Protocol, released with the ADR…
• AgentCordon — Sources: Homepage · GitHub repo ·…
• AgentDojo — A peer-reviewed, independent benchmark for prompt injection against tool-using AI agents.
• Agentforce (Salesforce) — Sources: Homepage
• AgentGateway — Sources: AgentGateway (repo)
• AgentShield — Sources: GitHub — affaan-m/agentshield ·…
• AutoGen — Sources: AutoGen (repo) · AutoGen docs · Unit 42 — AI Agen…
• Big Sleep (Google Project Zero + DeepMind) — Sources: Project Zero — From Naptime to Big Sleep (Oct 2024) ·…
• Cedar — Cedar is an open-source policy language and evaluation engine designed for fine-grained, application-level authorization.
• Claude Code Security — Sources: Announcement (Feb 20, 2026) ·…
• CodeMender (Google DeepMind) — Sources:…
• Codex Security — Sources: Original Aardvark announcement ·…
• CrewAI
• Cursor — Sources: Cursor (cursor.com)
• Agent Guard) — Sources: CyberArk Secrets Manager SaaS ·…
• CyberSecEval — Sources: Purple Llama / CyberSecEval (repo)
• DefenseBench — Sources: DefenseBench · BOTSv3 benchmark
• Firecracker — Firecracker is an open-source Virtual Machine Monitor (VMM) created by AWS and open-sourced under Apache 2.0.
• Garak — Sources: Garak (NVIDIA/garak repo) · Garak docs
• GKE Agent Sandbox — Agent Sandbox is an open-source Kubernetes controller that runs isolated, stateful, single-replica workloads — the shape an AI agent’s co…
• gVisor — gVisor is a Google-developed, open-source (Apache 2.0) container sandbox that provides kernel-level isolation without requiring a full vi…
• Kirin (Knostic) — Sources: Kirin (Knostic) ·…
• Lakera Guard — Lakera Guard is a commercial AI security API from Lakera (Swiss company) that provides real-time detection of prompt injection attacks, j…
• LlamaFirewall — Sources: LlamaFirewall paper, arXiv:2505.03574 (see the summary page) ·…
• Mallory — Sources:…
• MDASH (Microsoft Agentic Scanning Harness) — Sources:…
• Microsoft Agent 365 (with Entra Agent ID) — Sources:…
• Microsoft Security Copilot — Sources: Homepage · Microsoft Secure…
• Miggo Security — Sources: Miggo Security (homepage)
• Mindgard CART — Sources: Mindgard (homepage) ·…
• MOAK (Mother of All KEVs) — Sources: MOAK (homepage)
• Claude Mythos Preview (Anthropic) — Sources: Anthropic Project Glasswing landing page ·…
• Okta for AI Agents — Sources: Okta (homepage) ·…
• Onyx Platform (Onyx AI Control Plane) — Sources: Onyx Platform (homepage)
• Rego (Open Policy Agent) — Open Policy Agent (OPA) is a CNCF-graduated open-source policy engine (Apache 2.0).
• OpenAnt — Sources: Project page — openant.knostic.ai ·…
• Palo Alto Prisma AIRS (AI Runtime Security) — Prisma AIRS is Palo Alto Networks’ end-to-end AI security platform protecting the full lifecycle of AI applications and agents — model se…
• Promptfoo — Open-source LLM evaluation and red-teaming framework that runs YAML-defined test suites in CI to catch prompt regressions, vulnerability…
• Purple Llama — Meta’s umbrella project for open trust-and-safety tooling around generative AI.
• PyRIT (Python Risk Identification Tool) — Sources: PyRIT (repo) · PyRIT docs ·…
• RAPTOR — Sources: GitHub — gadievron/raptor · Mythos-ready paper §Appendix A Historical Precedent + PA 1…
• RedAI — Open-source terminal workbench for AI-driven vulnerability discovery with live-environment validation, authored by Kyle Polley under MIT.
• Smokescreen (Stripe) — Sources: Smokescreen (repo)
• Tenuo Warrant — Sources: Tenuo (homepage) · Tenuo core (repo)
• Toolshed (Stripe) — Stripe’s central MCP proxy / tool registry. Internal product (not open source as of Unprompted March 2026).
• Wiz AI-SPM — Sources: Wiz AI-SPM (homepage) ·…