Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets

Kurzinfo

Metadaten

  • Original (extern): Link oeffnen
  • Veroeffentlicht: 2026-08-11 10:24 UTC
  • Importiert: 2026-08-18 11:11 UTC
  • Quelle-ID: thn_global
  • uid_hash: 59dd090256e2d9d0ac11b0242381a9ced9954b790fdc39886f221ecdf11903ca

Inhalt

A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source code, and customer data without ever sending one obviously harmful instruction.

The trick can work even after a blunt version of the same theft is refused: split the request into fragments that each look routine, place them in channels the assistant already uses, and let

No data

Quellen-Details

Bezeichnung Name Kategorie Tags Zielgruppe Sprache Feed-URL
The Hacker News

thn_global

security_news - de https://feeds.feedburner.com/TheHackersNews