Threat

CPython Sandbox Escape Threatens AI Inference

Page published

Earliest dated coverage: 6 Nov 2026 · First observed: 16 Nov 2026 · Latest dated coverage: 6 Nov 2026

Coverage timeline

6 Nov 2026brandefense.io

Single-source analysis — one report is available.

Why it matters

Backdoored chat templates can turn model rendering into server-side code execution, making template files a critical part of model supply-chain review alongside model weights.

A CPython memory-safety flaw reportedly lets a malicious model chat template escape Jinja sandboxing and execute code with an AI inference server's privileges. RunSybil demonstrated the attack against vLLM using a backdoored Qwen2.5-0.5B-Instruct model; the report says the fix has not reached Python 3.12.