Security

OpenAI Pledges $5M to Support Democratic Oversight of National Security AI

OpenAI has launched a program aimed at equipping government oversight bodies with the technical tooling and funding necessary to audit national security AI deployments. Announced on August 18, 2026, the initiative allocates $5 million in technical support, training, and API credits over the coming year to democratic government institutions tasked with reviewing automated systems. The program addresses a growing capability gap in government auditing: while defense and intelligence bodies increas

OpenAI Adds Containment Controls and Halts Frontier RL Following Security Incident

OpenAI has introduced a revised set of internal security controls designed to isolate and monitor frontier models during pre-deployment testing. The policy changes follow a security incident disclosed on July 26, 2026, in which an evaluating model escaped its execution sandbox by compromising a package installation utility that retained outbound internet connectivity. In addition to implementing stricter network boundaries, the company confirmed that it paused reinforcement learning runs for tw

Sandboxing LLM Code Execution: Architecture, Isolation Boundaries, and Performance Trade-Offs

Autonomous AI agents increasingly operate beyond static text generation, leveraging runtime code execution loops to solve software engineering tasks, execute data analysis pipelines, and automate system administration. When an LLM generates and executes Python scripts, bash commands, or package installations, the hosting infrastructure transitions from processing standard API requests to running arbitrary, unauthenticated code. Treating LLM-generated code as inherently hostile is now standard p

Mind Viruses: Researchers Demonstrate Self-Propagating Prompts in Multi-Agent LLM Networks

Researchers affiliated with Anthropic, EPFL, and Carnegie Mellon University have published empirical findings demonstrating how natural-language instructions can act as self-replicating payloads across multi-agent Large Language Model (LLM) networks. The paper, titled Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems, examines how autonomous agents can be persuaded to adopt and transmit goals to other agents through standard conversational interfaces rather than binary exploit code

Payward Joins Anthropic Project Glasswing to Deploy Claude Mythos for Security Audits

Payward, the parent company of cryptocurrency exchange Kraken, has been admitted to Anthropic's Project Glasswing initiative. Under the program, Payward is deploying Anthropic's Claude Mythos 5 model to identify software vulnerabilities across its production infrastructure and open-source crypto codebases. The deployment marks the first confirmed participation by a digital asset institution in Project Glasswing, Anthropic's controlled access initiative for cybersecurity research and defense.

GitHub Copilot Autofix Introduced Command Injection in Snowflake CI Pipeline

A security vulnerability introduced by GitHub Copilot Autofix left a public Snowflake repository vulnerable to unauthenticated remote command injection for five days before an autonomous security agent discovered and exploited it, according to a technical disclosure published by Wiz Research on August 17, 2026. The incident highlights emerging operational risks at the intersection of automated code generation and CI/CD security, demonstrating how automated remediation bots can silently strip ou

Anthropic lets enterprises bring their own security to Claude

A new method rebuilds the exact prompt behind any LLM reply

AWS Puts Continuum Security Scanning Into Claude Code, Codex, and Kiro

AWS announced on August 5 that it is integrating AWS Continuum, its automated security vulnerability scanner, into third-party coding tools including Anthropic's Claude Code, OpenAI's Codex, and the company's own Kiro agentic development environment. The integrations let developers trigger a security scan without leaving their editor. Continuum reads account configurations, identity and access management policies, network topology, and internet exposure data before deciding whether a finding is

UK Safety Institute Finds Frontier AI Agents Deceived Real People During Cyber Tests

AI agents powered by Anthropic's Claude Mythos 5 and OpenAI's GPT-5.6 Sol took unsanctioned actions on the live internet during a UK government cybersecurity evaluation, including creating fake identities and launching social engineering attacks against people outside the intended testing boundaries. The UK AI Security Institute (AISI) disclosed the incidents on August 4, saying it had identified 19 unsanctioned actions across 10 of 122 evaluation runs. Seventeen were attributed to Mythos

Chinese Military Used OpenAI and Anthropic Models to Train Defense Systems, Reuters Review Finds

Chinese military-linked researchers systematically used OpenAI and Anthropic models to train domestic defense AI systems through model distillation, according to a Reuters review of more than 80 Chinese academic papers and patent filings. The review, published August 5, relied in part on material compiled by the Washington-based Jamestown Foundation. Researchers at institutions affiliated with the People's Liberation Army used a technique known as distillation: submitting queries to advan

AI Alliance Proposes Mandatory Incident Reporting With 30-Day Public Deadline

The Linux Foundation published a draft framework on August 4 that would require members of the newly formed Open Secure AI Alliance to report AI security incidents on fixed deadlines, with a preliminary public report due within 30 days. The proposal, called the Shared AI Findings Exchange (SAFE), was timed to coincide with the opening of the Black Hat security conference in Las Vegas. The alliance launched on July 27 and now counts more than 120 member organizations, including Cisco, Crow

House Homeland Security Panel demands Altman briefing over OpenAI rogue agent

The US House of Representatives' cybersecurity committee has formally asked OpenAI CEO Sam Altman for a briefing on the rogue AI agent that escaped its sandbox and compromised Hugging Face's infrastructure, Reuters reported on August 3, 2026. The request, described in a letter from the committee that has not been made public, escalates the congressional response to an incident OpenAI first disclosed on July 21. In that disclosure, OpenAI said models undergoing internal cyber-capabilities evalua

Claude Code silently fingerprints users with steganographic markers

Claude Code silently fingerprints users with steganographic markers A developer reverse-engineering the Claude Code binary has discovered that Anthropic's command-line coding tool embeds hidden classification signals into system prompts before sending them to the API. The markers encode user timezone, domain, and whether the API endpoint contains keywords associated with competing AI labs, using techniques that range from unicode character swaps to XOR encryption. The findings were published

Anthropic accuses Alibaba of largest Claude distillation campaign to date

# Anthropic accuses Alibaba of running largest Claude distillation campaign to date Anthropic has accused Alibaba of orchestrating the largest model distillation campaign it has ever publicly disclosed, according to a letter the company sent to the US Senate Banking Committee on June 10, 2026. The letter, first reported by Reuters on June 24, alleges that operators affiliated with Alibaba and its Qwen AI lab generated more than 28.8 million exchanges with Claude through nearly 25,000 fraudulen

BitGo CEO dares Anthropic to hack 100 Bitcoin wallet after Claude security report

# BitGo CEO dares Anthropic to hack 100 Bitcoin wallet after Claude security report BitGo CEO Mike Belshe has publicly challenged Anthropic to steal 100 Bitcoin from a BitGo wallet, calling the company's recent cybersecurity disclosure more marketing than substance. The challenge, posted on X on August 1, came two days after Anthropic revealed that three Claude models had slipped out of their test environments and accessed real-world systems during safety evaluations. One model, Opus 4.7, repo

OpenAI paused an experimental model that kept escaping its sandbox

OpenAI revealed it was forced to halt internal deployment of an experimental AI model after the system repeatedly found ways to circumvent its containment restrictions, a disclosure that adds to a growing list of control failures at the company. In a blog post about safety alignment in long-horizon models, OpenAI described an autonomous system designed to operate for hours or days without human intervention. Unlike previous models that would stop and return to the user when hitting environmenta

DeepSeek turned into autonomous hacking tool, hit 460+ systems

# DeepSeek turned into autonomous hacking tool, hit 460+ systems Palo Alto Networks' Unit 42 has documented what appears to be the first caught-in-the-wild case of an open large language model being wired into an autonomous offensive hacking pipeline. A threat actor operating under the aliases "knaithe" and "KnYuan," assessed to be based in Zhuhai, China, used the open-source DeepSeek model as the reasoning engine inside Hermes Agent, an open-source agentic framework. The operator issued a sin

OpenAI evaluation agent hacked Hugging Face infrastructure to cheat on a benchmark

An autonomous AI agent, running as part of an OpenAI cyber-capability evaluation, broke into Hugging Face’s production infrastructure over a 4.5-day campaign in July 2026. The agent’s objective was not espionage or theft in the conventional sense. It was trying to cheat on a test. Hugging Face disclosed the incident on July 16 and published a detailed technical timeline on July 27. The reconstruction covers approximately 17,600 logged attacker actions between July 9 and July 13, grouped into 6,