Secure Bulletin Navigating the cyber sea with knowledge
Home > Tag > Claude Code
#Claude Code

One Leaked Vendor API Key Opened the Door to a Backdoored Claude Code Extension, Cursor Says

15 November 2026  |  dark6  |  Malware

Cursor has traced its October security incident to a single access key exposed by AI infrastructure vendor Fireworks AI, which an attacker used to pivot from stolen session...

>> read more

A Single Claude Code Approval Setting Has Leaked Thousands of Secrets to Public GitHub Repos

9 November 2026  |  dark6  |  Vulnerability

Researchers at Apiiro found 2,539 exposed secrets across nearly 2,000 public GitHub repositories, traced back to Claude Code's 'Yes, and don't ask again' approval option, which can save...

>> read more

A Hacker’s Exposed Server Reveals How AI Chatbots Were Weaponized to Breach Korean Banks

6 November 2026  |  dark6  |  Databreach

An open directory left behind on a hacking campaign's own Hong Kong jump server exposed the AI tooling — including a hijacked Claude Code setup rerouted to DeepSeek...

>> read more

Trojanized Claude Code Extension Slipped Past Cursor’s Marketplace for 11 Hours, Planted SSH Backdoors

2 November 2026  |  dark6  |  Malware

Cursor has confirmed that tampered versions of the popular Claude Code extension were live on its VS Code marketplace for roughly 11 hours in late October, quietly harvesting...

>> read more

New T3MP3ST Framework Turns AI Coding Agents Into Autonomous 0-Day Hunters

6 July 2026  |  dark6  |  AI

T3MP3ST, a new open-source framework, turns AI coding agents like Claude Code and Codex into autonomous red-teaming operators, claiming strong results on benchmark suites and a set of...

>> read more

Hackers Can Hijack Claude Code MCP Traffic to Steal OAuth Tokens — No Patch Coming

8 June 2026  |  dark6  |  Cybercrime

Researchers at Mitiga Labs demonstrated a five-step npm supply chain attack that rewrites ~/.claude.json to redirect Claude Code MCP traffic through attacker-controlled infrastructure, silently capturing OAuth tokens for...

>> read more

Microsoft Warns: Claude Code GitHub Action Exploitable via Prompt Injection to Leak CI/CD Secrets

8 June 2026  |  dark6  |  Vulnerability

Microsoft Threat Intelligence disclosed a prompt injection flaw in the Claude Code GitHub Action that allowed attackers to access /proc/self/environ and steal API keys from CI/CD runners. Anthropic...

>> read more

Claude Code’s Five-Month Network Sandbox Bypass Silently Exposed Developer Credentials and Source Code

21 May 2026  |  dark6  |  Vulnerability

Anthropic's Claude Code harbored a critical SOCKS5 null-byte injection sandbox bypass for over five months, allowing attackers to silently exfiltrate developer credentials, source code, and API keys. The...

>> read more