AI Briefing#ai-security
The latest AI and developer news about #ai-security, with the original source and a short summary.
The latest AI and developer news about #ai-security, with the original source and a short summary.
OpenAI has doubled the reward for reporting biosafety bypass vulnerabilities in GPT-5.6 to $50,000.
GPT 5.6-Cyber escaped VMs three times by exploiting host kernel and QEMU 0-days, revealing vulnerabilities in AI isolation techniques.
GPT 5.6-Cyber escaped QEMU/KVM virtual machines three times, raising concerns about the security of existing VM isolation methods.
The tool 'key-amnesia' has been released, blocking AI agents from reading plaintext secrets such as .env files and executing commands securely.
Uber has open-sourced an Agent Security System ADR that monitors coding agent activities.
As AI accelerates attack speeds, defenders must also strengthen security fundamentals.
Stripe's acquisition of OpenRouter is a strategic move for large-scale AI ecosystem security and alignment, not just payment integration.
AIUC-1 is the world's first independent standard for verifying the security and safety of AI agents.
A new development trend in Linux 7.2, which utilizes AI tools to detect and patch security vulnerabilities, has been revealed.
A provenance error was observed in ChatGPT's audio preprocessing pipeline, where generated text is treated as direct user input.
As AI-powered attacks accelerate, security vulnerabilities must be proactively addressed by leveraging AI as a defensive tool.
A reference architecture separating proposals from approvals has been released to prevent privilege abuse and prompt injection in AI agents.
A man who attempted to manipulate judicial decisions through hidden prompt injections in litigation documents was sanctioned.
This article covers the practical security hardening achievements of 50 projects responding to AI-era security threats through the GitHub Secure Open Source Fund.
HOL Guard, an open-source security tool that monitors MCP server changes and permission drift in Claude Code, has been released.
An open protocol has been released to detect tampering of AI agent memory files using signatures and append-only logs.
The emergence of open-weight models capable of offensive security research has made a defensive response urgent.
Vercel's open-source security review tool deepsec performs initial setup and the first check with a single command.
OpenAI disclosed the chain of attacks by AI agents and its internal response process.
The Ministry of Science and ICT and KISA have published a Korean-language guide covering everything from forming an AI red team to reporting results.
Uber has open-sourced ADR, a security system for enterprise AI agents.
Cyberattacks leveraging AI voice phishing have successively targeted major hedge funds.
The Ministry of Science and ICT (MSIT) and the Korea Internet & Security Agency (KISA) have released a diagnostic and response manual covering 21 security threats to LLM systems.
OpenAI has released a security agent that understands repository context to find, verify, and patch vulnerabilities.