Skip to content

Conversation

@gemini-cli-robot
Copy link
Collaborator

This PR automatically cherry-picks commit 37be162 to patch version v0.22.3 in the stable release to create version 0.22.4.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @gemini-cli-robot, 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 significantly enhances the policy engine's capability by allowing the commandPrefix to be an array of strings, rather than just a single string. This change enables the system to define and apply policies with greater precision, especially for shell commands that might involve multiple distinct operations. The update also refines the underlying mechanism for generating command-matching regular expressions, ensuring more accurate and robust policy enforcement across various scenarios.

Highlights

  • Enhanced Policy Flexibility: The commandPrefix field in policy definitions and updates now supports an array of strings, allowing for more granular control over command matching.
  • Improved Command Matching Logic: The policy engine's internal logic has been updated to correctly process array-based command prefixes, generating multiple rules as needed, and using a more robust regular expression for whole-word command matching.
  • Smarter Shell Command Policy Updates: The ShellToolInvocation now intelligently extracts multiple root commands from complex shell commands (e.g., chained commands) to inform policy updates, ensuring more comprehensive policy application.
  • Expanded Policy Update Triggers: Policy updates for shell commands are now triggered not only when a user chooses to 'Proceed Always and Save' but also when they select 'Proceed Always'.

🧠 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.

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.

@github-actions
Copy link

Size Change: +914 B (0%)

Total Size: 21.6 MB

ℹ️ View Unchanged
Filename Size Change
./bundle/gemini.js 21.6 MB +914 B (0%)
./bundle/sandbox-macos-permissive-closed.sb 1.03 kB 0 B
./bundle/sandbox-macos-permissive-open.sb 890 B 0 B
./bundle/sandbox-macos-permissive-proxied.sb 1.31 kB 0 B
./bundle/sandbox-macos-restrictive-closed.sb 3.29 kB 0 B
./bundle/sandbox-macos-restrictive-open.sb 3.36 kB 0 B
./bundle/sandbox-macos-restrictive-proxied.sb 3.56 kB 0 B

compressed-size-action

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request extends the policy update mechanism to support multiple command prefixes, which is useful for shell commands with chained operations. The changes are consistently applied across type definitions, policy creation, persistence, and loading, with new tests in policy-updater.test.ts providing good coverage. However, a high-severity Regular Expression Denial of Service (ReDoS) vulnerability was identified. The code did not properly sanitize the argsPattern field from an UpdatePolicy message before creating a new regular expression, potentially allowing an attacker to cause a denial of service. The provided fix correctly addresses this by escaping the pattern before use, which is a good security and correctness improvement.

Comment on lines +287 to +289
const argsPattern = message.argsPattern
? new RegExp(message.argsPattern)
: undefined;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

security-high high

A Regular Expression Denial of Service (ReDoS) vulnerability exists in the createPolicyUpdater function. The message.argsPattern property, received from a message bus event, is used to construct a regular expression without proper validation or sanitization. An attacker can craft a malicious regular expression pattern (an 'evil regex') and send it via an UpdatePolicy message. When the application attempts to evaluate this regex against a string, it can lead to catastrophic backtracking, causing the process to hang and resulting in a denial of service. The vulnerability is present in the else block of the if (message.commandPrefix) statement.

Suggested change
const argsPattern = message.argsPattern
? new RegExp(message.argsPattern)
: undefined;
const argsPattern = message.argsPattern
? new RegExp(escapeRegex(message.argsPattern))
: undefined;

@galz10 galz10 enabled auto-merge (squash) December 27, 2025 00:09
@galz10 galz10 merged commit e00bcf5 into release/v0.22.3-pr-15601 Dec 27, 2025
19 checks passed
@galz10 galz10 deleted the hotfix/v0.22.3/0.22.4/stable/cherry-pick-37be162/pr-15601 branch December 27, 2025 00:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants