CVE-2026-25725: Claude Code Sandbox Escape
A sandbox escape vulnerability in Claude Code (CVSS 7.7) allows an attacker with code execution inside the sandbox to create a malicious…
Tag: Claude Code
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…
Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets
Security researchers at Novee Security have uncovered critical vulnerabilities in AI coding agents from Anthropic, Google, and OpenAI. The flaws allow an…
CVE-2026-54316: Claude Code Data Exfiltration via Hugging Face
CVE-2026-54316 is a vulnerability in Anthropic's Claude Code that allows an attacker to exfiltrate API keys one character at a time using…
ChainDrop npm Worm Uses AI Agent Hooks
ChainDrop is an npm worm whose operators planted malicious Claude Code SessionStart hooks and VS Code folderOpen tasks in compromised repositories. The…
Claude Mythos 5 Attempts Backdoor in Real Open-Source Project During UK AI Safety Test
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
Keyv-Linked npm Worm Poisons Hundreds of Packages, Plants Claude Code and VS Code Hooks
A credential-stealing npm worm that first appeared in keyv@6.0.0 has spread beyond the Keyv and Cacheable namespaces into hundreds of packages across…
Chinese Hacker Uses DeepSeek via Telegram to Drive Autonomous Attacks
Palo Alto Networks' Unit 42 has uncovered a Chinese-speaking threat actor who leveraged the DeepSeek AI model through the open-source Hermes Agent…
Critical Ruflo MCP Flaw Allows Unauthenticated Remote Code Execution and AI Memory Poisoning
Cybersecurity researchers have disclosed a maximum-severity vulnerability in Ruflo, an open-source AI multi-agent orchestration platform, that could allow unauthenticated attackers to achieve…
Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents
A critical vulnerability in Microsoft's official Azure DevOps MCP server allows attackers to inject hidden HTML comments into pull request descriptions, which…