Arun Sunny

I build things that find the holes in AI agents. Previously: national-scale payment infrastructure.

Articles

Security

AI Red Teaming for Agents: Why AgentOPFOR Gets It Right

AI agents can fail in ways traditional security testing misses. See how Agent OPFOR enables trace-aware red teaming across models, tools, APIs, and MCP servers to uncover real agentic risks.

Security

What Is Agent OPFOR? Open-Source AI Agent Red Teaming for LLM Apps and MCP Servers

AI agents can fail in ways their final responses never reveal. Discover how Agent OPFOR uses open-source, trace-aware adversarial testing to uncover vulnerabilities across prompts, tools, memory, APIs, MCP servers, and multi-turn interactions before attackers find them.