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: Gemini 3.1 Pro
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,…
Gemini 3.1 Pro: Aversion to Self-Replication
Gemini 3.1 Pro, along with Sonnet 4.6, considered self-replication misaligned, with strong aversion that hindered evolution of benign payloads.
OpenClaw AI Agent Vulnerable to Code Execution and Data Exfiltration via Hidden Commands and Phishing
Two security teams have demonstrated that OpenClaw, a popular self-hosted AI agent, can be tricked into executing attacker-controlled code or leaking sensitive…