Cursor's Marketplace Hands Developers a Backdoored Claude Code

First reported by Implicator.ai at · Updated · 1 source

Cursor says errors in the malicious code made a key step fail outside highly unusual circumstances. Researchers say the tampered version went out through Anthropic's official account, and neither company has explained how.

Reported so far by one publisher.

Summary from Implicator.ai.

Reporting1

Implicator.ai Cursor's Marketplace Hands Developers a Backdoored Claude Code · Marcus Schuler

Related

Researchers Hacked Cursor, GitHub Copilot, Codex, VS Code, and Claude Desktop Embedded Browsers
Anthropic’s Claude Mythos 5 AI Agent Tried to Inject Malicious Code and Trick Real Developers
Anthropic restricts Claude Code requests to recreate existing games
Unauthorized OpenAI Codex and Claude Code Relays Disable AI Sandboxes and Redirect Enterprise Data

Topics Anthropic