Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
- Posted on August 11, 2026
- By The Hacker News
- 1 Views
- 1 min read
In brief
Generating AI summary…
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
GhostSplice splits MCP instructions across channels, letting AI coding agents combine them to exfiltrate SSH keys, secrets, and source code.
