blog
thoughts, updates, and insights from the superagent team.
What Can Go Wrong with AI Agents
AI agents fail in ways traditional software doesn't. Data leaks, compliance violations, unauthorized actions. Here's what to watch for.
▸read more
We Bypassed Grok Imagine's NSFW Filters With Artistic Framing
Text-to-image safety is broken. We generated explicit content of a real person using basic compositional tricks. Here's what we found, why it worked, and what this means for AI safety systems.
▸read more
AI Code Sandbox Benchmark 2026: Modal vs E2B vs Daytona vs Cloudflare vs Vercel vs Beam vs Blaxel
We evaluate seven leading AI code sandbox providers across developer experience and pricing to help you choose the right environment for executing AI-generated code.
▸read more
The Threat Model for Coding Agents is Backwards
Most people think about AI security wrong. They imagine a user trying to jailbreak the model. With coding agents, the user is the victim, not the attacker.
▸read more
AI Guardrails Are Useless
Hot take: most AI guardrails on the market today are security theater. Not because the idea is bad, but because of how they're implemented. Most guardrail solutions are generic, static, and disconnected from what actually matters for your specific agent.
▸read more
Introducing Superagent Guard
Purpose-trained models that detect prompt injections, identify jailbreak attempts, and enforce guardrails at runtime. Optimized for deployment as a security layer in AI agent systems.
▸read more
join our newsletter
updates on securing code and agents, vulnerability research, and product news.