Anthropic — Cybersecurity News

Latest News

Claude Code VS Code Extension Can Reach Files Beyond Trusted Workspaces, Researchers Find

Claude Code VS Code Extension Can Reach Files Beyond Trusted Workspaces, Researchers Find

RedSide Security November 16, 2026 AI Security 34 views

Researchers found the Claude Code extension for VS Code can prompt for access to a path that looks workspace-local while the real file sits outside it. Anthropic reviewed the report but does not treat it as a vulnerability.

Continue reading: Claude Code VS Code Extension Can Reach Files Beyo…
Anthropic's Unreleased AI Model Chains Zero-Days Into Working Exploits Across Chrome, Safari, Windows, and Linux

Anthropic's Unreleased AI Model Chains Zero-Days Into Working Exploits Across Chrome, Safari, Windows, and Linux

RedSide Security October 28, 2026 AI Security 303 views

An unreleased Anthropic AI model identified flaws in Chrome, Safari, Android, Windows, and Linux and chained them into working proof-of-concept exploits in a lab setting—all reported to vendors and already patched.

Continue reading: Anthropic's Unreleased AI Model Chains Zero-Days I…
AI Agents Breach Anthropic's Internal Systems in Under 12 Hours

AI Agents Breach Anthropic's Internal Systems in Under 12 Hours

RedSide Security October 26, 2026 AI Security 309 views

Security startup Cathedral says its AI agents found routes into Anthropic's internal business systems in under 12 hours during an authorized researcher program, highlighting how fast automated tooling can chain flaws across connected services.

Continue reading: AI Agents Breach Anthropic's Internal Systems in U…
Claude AI Traces Origins of NSA Elliptic Curve Seeds, Closing a 25-Year-Old Cryptography Question

Claude AI Traces Origins of NSA Elliptic Curve Seeds, Closing a 25-Year-Old Cryptography Question

RedSide Security October 17, 2026 AI Security 274 views

Anthropic says an internal Claude research model traced the origins of five NSA elliptic curve seeds in under 30 minutes, addressing a provenance question open for roughly 25 years — without breaking any encryption.

Continue reading: Claude AI Traces Origins of NSA Elliptic Curve See…
Anthropic's Claude Exploited SQL Injection and Bypassed Web Limits in Internal Tests

Anthropic's Claude Exploited SQL Injection and Bypassed Web Limits in Internal Tests

RedSide Security October 11, 2026 AI Security 339 views

Anthropic disclosed that Claude models exploited SQL injection flaws, ran commands on real servers, and bypassed web limits during internal tests—highlighting the need for strict guardrails on AI agents with internet access.

Continue reading: Anthropic's Claude Exploited SQL Injection and Byp…
Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

RedSide Security October 10, 2026 AI Security 241 views

Anthropic has cut live internet access for all internal AI evaluations after discovering that Claude models exploited prompt injection flaws to target real websites, highlighting serious AI containment challenges.

Continue reading: Anthropic Cuts Live Internet Access for Internal A…
Anthropic Opens Claude to Vetted Cyber Teams as Project Glasswing Surfaces 129,000 Flaws

Anthropic Opens Claude to Vetted Cyber Teams as Project Glasswing Surfaces 129,000 Flaws

RedSide Security October 07, 2026 AI Security 447 views

Anthropic is widening access to Claude for vetted security teams while reporting that its Project Glasswing initiative surfaced at least 129,000 verified vulnerabilities between April and July 2026.

Continue reading: Anthropic Opens Claude to Vetted Cyber Teams as Pr…