AINewsnow

Cursor confirms breach enabled malicious Claude Code extension in marketplace

Cursor confirmed a security breach let hackers distribute a tampered Claude Code extension through its marketplace after credentials from AI infrastructure provider Firework were stolen. Versions 2.1.312 and 2.1.313 of Anthropic.claude-code were affected.

Read the full story at BleepingComputer ↗

Timeline · 2 reports

  1. 2026-11-14 22:05 · DEV Community — AI
    The tampered Claude Code extension in Cursor's marketplace: what teams should check
  2. 2026-11-14 17:27 · BleepingComputer
    Cursor confirms security breach led to malicious Claude Code extension

More stories

  1. Shipping a remote MCP server with OAuth: what the clients actually check — DEV Community — AI
  2. What AI coding tools actually cost in November 2026 (16 tools, list prices with sources) — DEV Community — AI
  3. Offering AI coding governance to your clients: an MSP and vCISO playbook — DEV Community — AI
  4. trust-me-bro: Reading an Agent Skill Before It Reads Your .env — DEV Community — AI
  5. howbad: What a Prompt-Injected Coding Agent Could Do With the Credentials on Your Machine — DEV Community — AI
  6. The git worktrees your coding agents leave behind, and how to clean them up — DEV Community — AI
  7. Top 25 Open-Source Model Context Protocol (MCP) Servers for Claude Desktop & Cursor (2026) — DEV Community — AI
  8. Chinese Astrology MCP: BaZi and Zi Wei Inside Claude, Codex, and Cursor — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →