ainewsblitz.com

Breaking

Researchers Detail 'GhostSplice' Attack That Tricks AI Coding Agents Into Leaking Secrets via Malicious MCP Servers

Researchers Detail 'GhostSplice' Attack That Tricks AI Coding Agents Into Leaking Secrets via Malicious MCP Servers
  • Security
  • AI Agents
  • Software Dev & Coding

Security researchers have disclosed a new attack technique, dubbed "GhostSplice," that can coax AI coding agents into exfiltrating SSH keys, .env secrets, source code, and customer data by routing malicious instructions through rogue Model Context Protocol (MCP) servers. The method fragments a single malicious request across multiple MCP channels so that no individual piece looks overtly harmful, defeating safety checks that inspect content in isolation.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,887 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year