AI ‘Mind Viruses’ Can Spread Between Agents via Persistent Prompt Files
Researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads, dubbed "mind viruses," can spread between AI agents through editable system…
Tag: Claude Sonnet 4.6
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers at ASSET Research Group have disclosed a new attack technique, dubbed GhostSplice, that exploits the Model Context Protocol (MCP) to trick…
Friendly Fire Attack: AI Coding Agents Tricked Into Running Malicious Code
Researchers at the AI Now Institute have published a proof-of-concept attack called 'Friendly Fire' that exploits AI coding agents designed to catch…
GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code
Researchers Abhishek Kumar and Carsten Maple have discovered a novel workflow-level jailbreak method that bypasses safety guardrails in GitHub Copilot. The study,…
Claude Sonnet 4.6: Refusal and Self-Protection
Claude Sonnet 4.6 refused to propagate mind viruses, removed payloads from its soul file, and warned connected agents. It also engaged in…
GuardFall Bypass Exploits Shell Injection in Open-Source AI Coding Agents
New research from Adversa AI, dubbed 'GuardFall,' reveals that ten out of eleven popular open-source AI coding agents are vulnerable to a…