Skip to content
NewA calmer, faster ZeroHour
MalwaremediumExploited in the wild

Infostealers Target Claude, Cursor, Codex and Other AI Agents to Steal Credentials and Sensitive Data

GBHackersby Mayura Kathir ()4 min read4 · 1 read
Read at gbhackers.com
AI summary · glm-5.3-flashSummaries by Vani AI

Gen Digital researchers report infostealer families Amatera, Remus and CallbackBeaver now harvest Claude, Cursor and Codex agent data, including tokens and MCP configs.

Gen Digital researchers found commodity infostealers extending their collection rules to local AI coding agent data from Claude, Cursor, Codex, Cline, Continue and OpenCode on Windows and macOS. Amatera targets Cline and Continue, Remus targets Claude, Cursor and OpenCode, and CallbackBeaver added Claude and Cursor with more than 5,000 samples observed in 30 days; Djinn Stealer hits Claude, Codex, Gemini, Cline, OpenCode and Kilo on macOS. Stolen data includes access and refresh tokens, prompt histories, conversation databases and MCP configurations holding API keys, potentially exposing connected source-control, cloud and ticketing systems. Remus is assessed as a Lumma Stealer variant using EtherHiding C2 resolution via Ethereum smart contracts.

Key facts
  • Agent data theft can expose AI tokens, MCP credentials, prompt histories and proprietary source code.
  • Remus assessed as a Lumma Stealer variant using Ethereum-based EtherHiding C2.
  • Detections were recorded among tens of thousands of protected users, not confirmed infections.
  • Recommend using OS-backed keychains and short-lived, narrowly scoped MCP credentials.
  • Infostealers update targets remotely via dynamic collection rules, no payload rebuild needed.
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat
ATT&CK
T1005 Data from Local SystemT1552.001 Credentials in FilesT1555.003 Credentials from Web Browsers
Tags
amateraclaudecredential-theftcursorinfostealerlumma-stealermcpremus
Vendors
Gen Digital
Products
ClaudeCursorCodexClineContinueOpenCodeModel Context Protocol
Malware
AmateraRemusCallbackBeaverDjinn StealerLumma StealerBeeStealerSTG StealerHydraStealerAPEX StealerOtter Stealer

From the original article

4 min read at gbhackers.com

Information-stealing malware is expanding its collection logic to target locally stored data from AI coding agents, including Claude, Cursor, Codex, Cline, Continue, and OpenCode.

GBHackers

By Mayura Kathir · gbhackers.com

Read the full article at GBHackers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.