Jens Ernstberger
Co-founder, Kontext
Jens Ernstberger writes about AI agent security, runtime authorization, MCP, OAuth, credential management, and least-privilege enforcement for autonomous systems.
Focus areas
- AI agent security and runtime authorization
- MCP authorization, OAuth, and credential management
- Least-privilege enforcement for autonomous systems
- Compliance and audit trails for agentic workflows
Selected writing
- Agent Intent - No One Knows What It Means, But It's Provocative
Why runtime authorization for AI agents should evaluate action safety instead of trying to verify intent, with layered controls for unsafe tool use.
- Announcing Kontext
Kontext gives your AI agents proper identity, scoped access, and audit trails. So they work in production, not just in demos. One SDK. One line. This starts at kontext.require().
- How to Keep a Secret: Why Personal AI Assistants Like OpenClaw Are a Security Nightmare
OpenClaw has taken over Twitter as an autonomous AI assistant that reads your emails, executes shell commands, and browses the web. From unauthenticated access to credential sprawl to prompt injection - here's a security analysis of what's broken and what we can do about it.
- The API Key is Dead: A Blueprint for Agent Identity in the age of MCP
How to move agents from static API keys to standards‑based OAuth—covering MCP architecture, autonomy levels, escalation, federation, and enterprise needs.
- Should You Care About Prompt Injection? (Probably.)
Agents read untrusted content and turn it into actions. Sanitize → detect → enforce at tool boundaries to make that speed survivable.
- Read. Write. Own. Delegate.
The next great leap in the digital age isn't just about ownership—it's about intelligent delegation. Explore how autonomous agents can amplify our capabilities while maintaining our sovereignty.
- How to Fix the TanStack Supply Chain Attack
Learn how to fix the TanStack supply chain attack with clean version pins, credential rotation, package release cooldowns, split publish workflows, and runtime authorization.
- I Built a Credential Broker for AI Coding Agents in Go
AI agents need credentials to call APIs on your behalf. Kontext brokers short-lived, scoped tokens so secrets never touch disk and every action is auditable.