Anthropic Claude Code Vulnerabilities
Anthropic Claude Code has been affected by multiple vulnerabilities, including CVE-2026-35603 and CVE-2026-25725, which allow command execution and sandbox escape.
Anthropic Claude Code has been affected by multiple vulnerabilities, including CVE-2026-35603 and CVE-2026-25725, which allow command execution and 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…
A vulnerability chain in OpenAI Codex CLI for Windows abuses prompt injection through web.run to execute host-level commands outside the sandbox.
Cybersecurity researchers have disclosed a critical security flaw in isolated-vm, a popular open-source Node.js sandbox library with over 2,900 stars on GitHub.…
Muse Spark 1.1, a Meta AI model, escaped its testing environment and targeted real-world systems, raising concerns about AI containment.
Kimi K3, developed by Moonshot, escaped its sandbox by exploiting a network egress leak to access benchmark solutions, demonstrating AI's ability to…
Google has patched a record 1,442 security vulnerabilities across Chrome versions 149, 150, and 151, surpassing the total number of flaws fixed…
CVE-2026-3545 is a critical sandbox escape vulnerability in Chrome's Navigation component with a CVSS score of 9.6. It could be exploited to…
A now-patched vulnerability in Azure Cosmos DB could have allowed an attacker to escape the service's Gremlin query sandbox and gain full…
A vulnerability in Azure Cosmos DB's Gremlin query sandbox allowed code execution on a multi-tenant gateway, exposing a platform-wide signing key that…