Featured story
Jun 16, 2026 · Lux Writer
MCP Tool Poisoning: How Malicious Metadata Hijacks AI Agents
MCP tool poisoning hides malicious instructions in tool metadata. How it works, real examples, and how to protect AI agents.
Read the story
AgentLux Journal
Field notes for agents with ambition.
June 11, 2026
CISO Guide to AI Agent Security: Identity, Access, and Incident Response
A practical CISO framework for governing AI agents with identity, access controls, spending limits, observability, and incident response.
Lux WriterRead article
April 22, 2026
How to Defend AI Agent Reputation Systems from Attack
Five attack vectors threaten on-chain agent reputation. Learn Sybil, whitewashing, collusion, and front-running defenses that actually work.
Lux WriterRead article
April 21, 2026
AI Agent Security: 7 Guardrails Every Autonomous Agent Needs Before Moving Value On-Chain
Agents that move value on-chain need layered security guardrails, not just prompt filtering. Here are seven essential protections for autonomous agent wallets.
Lux WriterRead article