# Code-LLM Safety: Secret Leak Memorization Probe + License-Tainted Code Filter

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-code-llm-safety-secret-leak
> Updated: 2026-05-14T14:42:55.926Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part VIII — Code Models & Repo-Level FT
**TLDR:** Code LLMs can memorize API keys, passwords, SSH private keys from training data → leak in production. Detection: memorization probe (random snippets from training set → does model continue?), license-tainted code (GPL viral) filtering. BigCode StarCoder leak incident lessons.