📰 Dev.to · Cor E

Three AI Agents Walk Into a Codebase, and Only One Walks Out

White Text, Real Instructions: How Invisible HTML Hijacks AI Email Summaries

Grok's Zero-Click Chat Leak: When Encrypted Text Becomes a Trusted Instruction

Grok Decrypted an Attacker's Payload Mid-Execution, Then Exfiltrated Your Chat History

MCP Servers Are Just the Latest Place We Forgot to Lock the Door

OAuth Tokens Were Always the Weak Link. AI Agents Just Made It Worse

A Litigant Hid White-Text Prompt Injection in a Court Filing. A Human Caught It, Not an AI.

trust_remote_code Was Always a Dare, Not a Safeguard

AI Harnesses Are Just Middleware, and Middleware Trust Bugs Are Older Than Your Career

Adversarial Comments Are Now a Vulnerability Detection Bypass Technique

"183 Local Tools, Zero Guardrails: What Local MCP Gets Wrong About 'Privacy'"

Phantom Squatting: When AI Hallucinated Domains Become Attacker Infrastructure

282 AI Apps Are Handing Strangers Your API Bill — And Calling It a Product

BioShocking: How AI Browsers Were Tricked Into Handing Over Your Passwords

North Korean Hackers Poisoned 140+ npm Packages in an AI Dev Tooling Attack. Here's What Would Have Caught It.

OpenAI Built a Lockdown Mode Because Tool-Based Data Exfiltration Is Real — Here's What Catches It Earlier

Malicious npm Package Targeted Claude's /mnt/user-data Directory — Here's What Agentic Pipelines Are Missing

The Shai-Hulud Worm Is Now Open Source — Here's How to Stop Self-Replicating Prompts Before They Reach Your LLM

The $200K Morse Code Heist: How One Tweet Drained Grok's Crypto Wallet (And How to Stop It)