Blog
Thoughts, updates, and insights from the Superagent team.
Your RAG Pipeline Is One Prompt Away From a Jailbreak
RAG is marketed as a safety feature, but connect it to agents that browse, call APIs, or touch databases, and every document becomes a potential jailbreak payload. Learn how malicious files, knowledge base poisoning, and indirect prompt injection turn RAG into an attack surface—and how to defend against it.
Practical guide to building safe & secure AI agents
System prompts aren't enough to secure AI agents. As agents move from chatbots to systems that read files, hit APIs, and touch production, we need real runtime protection. Learn how to defend against prompt injection, poisoned tool results, and the 'lethal trifecta' with practical guardrails.
AI Is Getting Better at Everything—Including Being Exploited
As AI models become more capable and obedient, safety improvements struggle to keep pace. The GPT-5.1 safety score drop reveals a structural problem: capability and attack surface scale faster than safety.
Are AI Models Getting Safer? A Data-Driven Look at GPT vs Claude Over Time
Are frontier models actually getting safer to deploy—or just smarter at getting around guardrails? We analyze 18 months of Lamb-Bench safety scores for GPT and Claude models.
Introducing Lamb-Bench: How Safe Are the Models Powering Your Product?
We built Lamb-Bench to solve a problem every founder faces when selling to enterprise: proving AI safety without a standard way to measure it. An adversarial testing framework that gives both buyers and sellers a common measurement standard.
VibeSec: The Current State of AI-Agent Security and Compliance
Over the past weeks, we've spoken with dozens of developers who are building AI agents and LLM-powered products. The notes below come directly from those conversations and transcripts.
Join our newsletter
We'll share announcements and content regarding AI safety.