fix: use the sessionId of sandbox instead of random string, so we can…

[qijiang17]

`
// 1. Set the sessionId of sandbox
BaseSandbox baseSandbox = new BaseSandbox(sandboxService, userId, sessionId);

// 2. Find mounted files by sessionId
@GetMapping("/file/list/{sessionId}")
public ResponseEntity<List> listDocuments(@PathVariable String sessionId) {
try {
Path workspacePath = Paths.get(System.getProperty("user.dir"), "sessions_mount_dir", sessionId);
if (!Files.exists(workspacePath)) {
return ResponseEntity.ok(List.of());
}
List files = Files.list(workspacePath)
.filter(Files::isRegularFile)
.map(p -> p.getFileName().toString())
.collect(Collectors.toList());
return ResponseEntity.ok(files);
} catch (Exception e) {
return ResponseEntity.internalServerError().build();
}
}
`

[gemini-code-assist]

Summary of Changes

Hello @qijiang17, 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 refactors how session IDs are handled during the sandbox creation process. The change ensures that the sessionId used for creating and managing sandbox containers, particularly for mounting directories, is consistently derived from the sandbox object itself. This promotes better session management and predictability, aligning the container's session ID with the sandbox's established ID.

Highlights

• Session ID Consistency: The method for generating the sessionId within SandboxService.createContainer has been updated. Instead of generating a new random string, it now retrieves the sessionId directly from the sandbox object passed as an argument, ensuring consistent identification.

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. ↩

[cla-assistant]

All committers have signed the CLA.

[gemini-code-assist]

Code Review

This pull request correctly modifies the sandbox creation process to use the provided sessionId instead of a random string. This is a good change for associating containers with sessions. However, this introduces a critical path traversal security vulnerability because the sessionId, which can be user-controlled, is used to construct a file path without validation. This must be addressed before merging.

[gemini-code-assist]

The sessionId obtained here is used on line 164 to construct a directory path. As the PR description indicates, the sessionId can come from a user-controlled source like a URL path parameter. This creates a critical path traversal vulnerability. A malicious user could provide a sessionId like ../../sensitive-data to create directories and potentially mount host paths outside of the intended sessions_mount_dir.

To mitigate this, you must validate the sessionId to prevent path traversal. Here is a robust way to do it using java.nio.file.Path:

// After getting the sessionId
Path mountPath = Paths.get(currentDir, default_mount_dir, sessionId).toAbsolutePath().normalize();
Path basePath = Paths.get(currentDir, default_mount_dir).toAbsolutePath().normalize();

if (!mountPath.startsWith(basePath)) {
    throw new IllegalArgumentException("Invalid sessionId, potential path traversal attempt.");
}

String mountDir = mountPath.toString();
// ... then use mountDir

This ensures that the resolved path for the session's mount directory is always inside the expected base directory.