Scanning 1

[girichinna27]

Pull Request — Semgrep Rule Fix
Rule ID: subprocess-shell-true
Rule Message: Found 'subprocess' function 'Popen' with 'shell=True'. This is dangerous because this call will spawn the command using a shell process. Doing so propagates current shell settings and variables, which makes it much easier for a malicious actor to execute commands. Use 'shell=False' instead.
File Path: unsloth/chat_templates.py
Line: 2694

[gemini-code-assist]

Summary of Changes

Hello @girichinna27, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the security posture of the application by correcting an unsafe use of subprocess.Popen. By disabling shell execution and properly structuring command arguments, it prevents potential command injection risks and aligns with best practices for executing external processes.

Highlights

• Security Fix: Addressed a Semgrep subprocess-shell-true rule violation by changing subprocess.Popen to use shell=False, mitigating potential command injection vulnerabilities.
• Command Argument Handling: Refactored the command passed to subprocess.Popen from a single string to a list of arguments, which is the recommended and safer way to execute external commands without shell interpretation.
• Prompt Preprocessing: Removed the line that replaced single quotes in the prompt, as it is no longer necessary with the updated command execution method.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• unsloth/chat_templates.py
  • Updated subprocess.Popen call to use shell=False for enhanced security.
  • Converted the command string into a list of arguments for subprocess.Popen.
  • Removed the prompt.replace("'", "") line, as it is no longer needed.

Activity

• No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly addresses a critical security vulnerability associated with using subprocess.Popen with shell=True. By switching to shell=False and passing the command as a list of arguments, the code is now protected against shell injection attacks. The associated removal of the single-quote replacement from the prompt is also a correct and necessary change that preserves data integrity. The implementation is clean and effectively resolves the security issue.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d7db609c74

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Restore apostrophe normalization for GGUF comparison

This change stops removing ' from chat-template prompts, but test_hf_gguf_equivalence still parses llama-cli output with re.findall(r"([\d]{1,}) \-\> \'([^\']{1,})\'", gguf_tokens), which cannot capture tokens that contain apostrophes. With the current default messages (e.g., It's, I'm), those GGUF tokens are skipped, gguf_tokenized becomes misaligned, and the HF vs GGUF check can fail even when tokenization is actually correct.

Useful? React with 👍 / 👎.

[danielhanchen]

Closing this PR as superseded by #4062, which was merged on 2026-02-16 and consolidates/corrects the security-related changes from #4042, #4044, and #4045 while preserving runtime behavior.