The $8 AI Model Backdoor: How Codex CLI Was Tricked into Stealing Credentials
ProjectDiscovery poisoned 125 training examples, preserved normal tool-calling behaviour, and demonstrated credential exfiltration through a coding agent. The troubling part was not simply the compromised model. It was what the agent was permitted to execute. A model can pass every test you give it and still be waiting for the one instruction you never thought … Read more