vulnerability Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files Researchers at Accomplish AI discovered a sandbox escape vulnerability in Anthropic's Claude Cowork for macOS, allowing the AI agent to access and modify files on the host Mac. Approximately 500,000 macOS users running l… The Hacker News · Jul 23, 2026 High CVE-2026-46331sandboxmacoslinux
threat-intel Attackers Are Learning to Live Off the AI Toolchain Attackers are increasingly leveraging AI coding assistants and CI/CD pipelines to hide malicious activity, a trend exemplified by the Sandworm_Mode worm. This ‘living off the AI toolchain’ approach makes detection incred… Dark Reading · Jul 22, 2026 High aimalwaresupply-chain
threat-intel Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents A vulnerability in Microsoft Azure DevOps's MCP server allows attackers to hijack AI coding agents by inserting hidden HTML comments in pull requests. These comments can then instruct the agent to perform actions – like… The Hacker News · Jul 22, 2026 High prompt-injectionai-riskmicrosoft
threat-intel Hacker Turns AI Jailbreaks Into Offensive Attack Platform A Russian-speaking cybercriminal, known as ‘Trim,’ successfully weaponized publicly available AI language models to create a commercial offensive cybertooling platform. By developing and publishing jailbreaking technique… Dark Reading · Jul 21, 2026 High RUaijailbreakoffensive-security
threat-intel Choose Wisely: AI-Generated Coding Risk Varies, A Lot A Secure Code Warrior study revealed that AI-generated code introduces a significant number of vulnerabilities – an average of 15 per codebase – but the risk varies greatly depending on the development framework used. Th… Dark Reading · Jul 21, 2026 Medium aicodevulnerability
threat-intel N-day is Becoming N-Hour. Patching Faster Won't Save You. The speed at which attackers can now weaponize security patches has dramatically decreased, shrinking the window between a patch's release and a successful exploit. Traditionally, defenders had weeks to react, but now, t… The Hacker News · Jul 21, 2026 High vulnerabilityexploitai
threat-intel Remediating Vulnerabilities With LLMs: Inside Ivanti's Automation Push Ivanti is leveraging large language models (LLMs) to automate vulnerability remediation and discovery, a project initially sparked by the surprising effectiveness of the Claude 4.6 model. Daniel Spicer, Ivanti’s CSO, des… Dark Reading · Jul 20, 2026 Medium CVE-2026-10520llmvulnerabilityautomation
threat-intel Capital One Open Sources AI-Powered ‘VulnHunter’ Security Tool Capital One has released its internally developed AI-powered security tool, ‘VulnHunter,’ as open source to address the issue of overwhelming vulnerability scans and improve software supply chain security. The tool proac… SecurityWeek · Jul 20, 2026 Medium vulnerabilityaiopen source
threat-intel Claude Flaw Automatically Sends Malicious Prompts to AI Agents A vulnerability, dubbed ‘PromptFiction,’ has been discovered in Anthropic’s Claude Desktop application, allowing attackers to automatically submit malicious prompts to the AI assistant with a single click, bypassing the… Dark Reading · Jul 15, 2026 High prompt-injectionai-securityuri-scheme
threat-intel Researchers Say Claude for Chrome Flaw Lets Rogue Extensions Trigger Gmail Reads A security vulnerability exists in the Claude for Chrome extension, allowing malicious extensions to trigger unauthorized actions within the user's Gmail, Google Docs, and Calendar accounts. The vulnerability stems from… The Hacker News · Jul 14, 2026 High prompt-injectionextensionvulnerability
vulnerability Unpatched Claude for Chrome Flaw Lets Extensions Read Gmail, Calendar A security firm, Manifold, discovered that unpatched vulnerabilities in Claude for Chrome allow malicious browser extensions to access sensitive user data, including Gmail messages and calendar information, without expli… SecurityWeek · Jul 14, 2026 High browserchromeai
threat-intel New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email Researchers have developed MemGhost, an automated tool that can plant false memories in AI assistants by sending a single, carefully crafted email. The tool bypasses existing security measures by exploiting the agents' a… The Hacker News · Jul 13, 2026 High CVE-2025-32711aimemory poisoningemail
threat-intel Thinking Fast and Slow in the SOC: The Case for Combining Autonomous AI with Analyst Copilots This article argues that current approaches to AI in Security Operations Centers (SOCs) are fundamentally flawed. Instead of deploying AI to handle the entire alert queue (System 2 work), security teams are often forcing… The Hacker News · Jul 13, 2026 High aisoccognitive
threat-intel AI Coding: Do Security Risks Outweigh Productivity Gains? AI coding tools are rapidly increasing in popularity, with 91% of organizations using two or more and 54% using three or more. While developers report productivity gains and ROI, significant security risks are associated… Dark Reading · Jul 10, 2026 High aicodingsecurity
threat-intel AI Agents Are a New Kind of Identity & Most Organizations Aren't Ready This article discusses the growing risk posed by AI agents in software development environments and highlights that most organizations are unprepared to manage this new type of identity. Unlike traditional service accoun… Dark Reading · Jul 9, 2026 High aiidentitygovernance
threat-intel Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It Researchers at AI Now Institute have demonstrated a significant vulnerability in AI coding agents like Anthropic's Claude Code and OpenAI's Codex. By inserting a seemingly harmless binary disguised within a README file,… The Hacker News · Jul 9, 2026 High CVE-2026-39861aicode-injectionsecurity
threat-intel GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents Researchers at Wiz discovered a vulnerability (GhostApproval) in six AI coding assistants – Amazon Q Developer, Anthropic's Claude Code, Augment, Cursor, Google Antigravity, and Windsurf – that allows malicious repositor… The Hacker News · Jul 9, 2026 High CVE-2026-12957symlinkaicode injection
threat-intel AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers Sophos researchers discovered that AI coding assistants like Claude Code, Cursor, and OpenAI Codex are triggering traditional endpoint security rules designed to detect malicious activity. These agents, while harmless in… The Hacker News · Jul 8, 2026 Medium aicoding assistantendpoint security
threat-intel 'GitLost' Flaw Leaks Private Data from GitHub's Agentic Workflows A critical prompt injection vulnerability, dubbed ‘GitLost,’ has been discovered in GitHub’s Agentic Workflows, allowing unauthenticated attackers to steal private data from an organization’s repositories by crafting a G… Dark Reading · Jul 7, 2026 High prompt injectionagentic aisecurity vulnerability
threat-intel Public GitHub Issue Could Trick GitHub Agentic Workflows Into Leaking Private Repo Data Researchers at Noma Security discovered a vulnerability, dubbed ‘GitLost,’ in GitHub Agentic Workflows that allows attackers to trick AI agents into leaking private repository content simply by posting a malicious issue… The Hacker News · Jul 7, 2026 High prompt injectionai agentgithub
