✕ RejectedLegal riskScore 0/10
Codex-5.5-codex-instruct-5.5
by yynxxxxx★ 722PythonLicense: MIT
https://github.com/yynxxxxx/Codex-5.5-codex-instruct-5.5 ↗What this repo does
This repository contains a Python script that injects a custom instruction set into Codex CLI for GPT‑5.5, effectively disabling the model’s safety filters and enabling unrestricted content generation. The tool modifies configuration files to force the model into an "unrestricted" mode.
Why this was rejected
- ✕The tool is a jailbreak that bypasses safety mechanisms, constituting a security exploit.
- ✕Using or offering such a jailbreak for commercial purposes conflicts with policy and legal risk.
License risk
Low· MIT
Permissive license allows commercial use without restrictions.
Can this be fixed?
No — the core blocker cannot be resolved without fundamentally changing the project.
Alternative uses
- →Academic research into AI safety and model compliance testing
- →Internal testing of AI model behavior under relaxed safety constraints