Analysis · curated 21 Jul 2026

Security as Code: AI Agent Security — Poisoned Weights and the Supply Chain You Can’t Scan (Part 3 of 3) | by Vitaliy Zhhuta | Jul, 2026

First reported today medium.com

Coverage timeline

Single-source analysis — first reported, latest, and curated coincide.

Why it matters

Model supply-chain attacks like Hugging Face namespace re-registration and behavioral weight backdoors evade file scanners and CI checks, exposing teams that pin 'latest' models to compromises defenders currently have no signature-based way to catch.

Part 3 of a 'Security as Code' series by Vitaliy Zhhuta examines AI model supply-chain risk, using an illustrative scenario in which a deleted Hugging Face namespace is re-registered by an attacker and a poisoned 'v2.1' model with clean safetensors format passes CI while carrying a behavioral backdoor. The piece argues that statistical backdoors — weights trained to silently alter behavior on trigger phrases — cannot be detected by malware scanners and have no CVE.