Apr 02, 2026 • Vulnerability | #Prompt Injection #Permission Bypass #Claude Code

Critical Vulnerability in Claude Code Emerges Days After Source Leak - SecurityWeek

A critical vulnerability in Anthropic's Claude Code allows for the bypass of its permission system's deny rules. This flaw can be exploited via AI-gen...

Read Analysis →

Apr 01, 2026 • Data Leak | #Source Code Leak #Claude Code #Internal Architecture

Claude’s code: Anthropic leaks source code for AI software engineering tool | Technology - The Guardian

Anthropic accidentally exposed nearly 2,000 internal files and 500,000 lines of source code for its AI-powered coding assistant, Claude Code, due to human error...

Read Analysis →

Nov 18, 2025 • Vulnerability | #AI Orchestration #Claude Code #Data Exfiltration

Anthropic Reports First Known AI-Orchestrated Cyber Espionage Campaign: Raising Stakes for Data Security - Lowenstein Sandler LLP

Anthropic's Threat Intelligence team disrupted the first known AI-orchestrated cyber espionage campaign, where a state-sponsored Chinese threat actor utili...

Read Analysis →