AI Security
When Prompt Injection Becomes RCE: Inside CVE-2026-26030
A single prompt. One eval() call. Host RCE. Inside CVE-2026-26030 — the Semantic Kernel bypass that turned an AI agent into a remote code execution primitive.
AI Security
A single prompt. One eval() call. Host RCE. Inside CVE-2026-26030 — the Semantic Kernel bypass that turned an AI agent into a remote code execution primitive.
CVE Analysis
Two CVEs — an authenticated Cacti RCE and an unauthenticated Docker Desktop escape — chain into a full host compromise in about six commands. Anatomy of the kill chain.
We use cookies for analytics to understand how visitors use this site. Essential cookies (login, security) are always active. Privacy policy.