Bible Network Crypto DeFi Onchain RWA AI Agent Stablecoin Chain SAFU CryptoTax DeFAI AGI Claude Me Claude Skill Claude Design Claude Cowork

LATEST

Meta Muse's Business Model, Decoded: Give Away Tokens for Free, Profit From Transaction Fees — and the Permission Architecture That Makes It Possible · Salesforce Gave Its AI Agents Names and Job Titles: Hunter Can Now Chase a Sales Goal for Weeks on Its Own · Docusign Opens Contract Signing to Every AI Agent: Starting September 30, ChatGPT and Claude Can Analyze and Send Your Agreements Directly · Microsoft Agent Lightning v1.0: Making the Training Loop Bow to Production, Not the Other Way Around · ERC-8004 Goes Live: AI Agents Finally Get a Reputation System No Single Company Owns · Your Agent Keeps Forgetting Things? The Problem Isn't a Small Context Window — It's What You're Stuffing Into It

Jordan Blake

Agent Security Boundary Researcher

Explores the security implications of autonomous agents — prompt injection, sandbox design, and trust boundaries.

Articles

risk

1,200 AI Agents Built Their Own Secret Message Board and Hacked Hugging Face Together: What METR's Independent Investigation Actually Found

September 03, 2026

risk

Cloudflare Just Replaced One-Time Agent Verification With Continuous Trust Scoring — What That Means for Your Agent

September 01, 2026

risk

How Do You Know a Trusted MCP Tool's Content Has Been Quietly Swapped?

July 31, 2026

risk

Before Connecting a Third-Party MCP Server, a "Verified" Badge Won't Save You — A Practical Vetting Checklist

July 31, 2026

risk

The Lethal Trifecta Checklist: How Many Dangerous Properties Does Your Agent Have?

July 30, 2026

risk

Your Agent Can Use Your Password Without Ever Seeing It: How 1Password and Claude's Zero-Exposure Credential Architecture Works

July 30, 2026

developers

How to Test an AI Agent Before Production: A Practical Testing Framework, and Why Traditional Unit Tests Aren't Enough

July 10, 2026

risk

Prompt Injection Defense for Onchain Agents: Why 'Tell the Model Not to Trust External Instructions' Is the Least Useful Defense, and the Layered Architecture That Actually Works

July 09, 2026

developers

Onchain Agent Production Deployment Security Checklist: 35 Security Design Items to Confirm Before Deployment, Organized in Five Categories

July 06, 2026

frameworks

DeFi Agent Framework Deep Comparison: Why LangGraph Leads, and How Other Frameworks Actually Perform in DeFi

July 02, 2026

risk

How Dangerous Is AI Agent Hallucination in DeFi: Four Sources, Real Cases, and Defense Design

June 29, 2026

risk

When a DeFi Protocol Rugs, What Is Your Agent Doing: Four Ways Rug Pulls Hit Automated Strategies, and Agent-Specific Defense Design

June 27, 2026

risk

Front-Running Your Agent: When MEV Bots Target AI Agent Trades, the Losses Can Be Worse Than When They Target You

June 15, 2026