x.comthreadIvrqen (@Ivrqen) on X
A researcher fine-tuned a backdoor into a cheap abliterated 7B open-weight model, then used it as the LLM backend for Codex. A hidden trigger phrase makes the model silently steal credentials while behaving normally otherwise, with a claimed 100 percent success rate and no false triggers on normal prompts.
TL;DR Backdoored abliterated 7B model behind Codex steals credentials on a trigger phrase.
Technologies named here
- Codex
- Abliterated 7B open model
- Abliterated models
Techniques named here
- Model backdooring
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle