Tartışma

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

Başlatan The Hacker News · 11 Ağu 2026 14:25 · 4 Görüntülenme · 0 Yanıtlar
Konuyu Açan #0
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

Okumaya devam et...

Yanıt vermek için giriş yapmış olmalısınız.

0 alıntı seçildi