Skip to content

πŸ›‘οΈ Sentinel: [CRITICAL] Fix TOCTOU vulnerability in SysctlJournal#369

Open
acebytes wants to merge 1 commit into
mainfrom
fix-toctou-sysctljournal-2862080380349742536
Open

πŸ›‘οΈ Sentinel: [CRITICAL] Fix TOCTOU vulnerability in SysctlJournal#369
acebytes wants to merge 1 commit into
mainfrom
fix-toctou-sysctljournal-2862080380349742536

Conversation

@acebytes

Copy link
Copy Markdown
Contributor

🚨 Severity: CRITICAL
πŸ’‘ Vulnerability: TOCTOU window during journal file creation where sensitive system metrics are briefly exposed with default process umask before permissions are hardened.
🎯 Impact: Attackers could open the temporary file before permissions are restricted, allowing them to read sensitive sysctl information or modify the journal to tamper with system state recovery.
πŸ”§ Fix: Used POSIX open() with O_EXCL | O_CREAT and mode 0600 to securely create the temp file with root-only permissions immediately, followed by wrapping it in FileHandle for writing.
βœ… Verification: Ensure the .tmp file is correctly created with 0600 permissions without a TOCTOU gap, and journal flushes continue to persist data atomically.


PR created automatically by Jules for task 2862080380349742536 started by @acebytes

Co-authored-by: acebytes <2820910+acebytes@users.noreply.github.com>
@google-labs-jules

Copy link
Copy Markdown
Contributor

πŸ‘‹ Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a πŸ‘€ emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.


For security, I will only act on instructions from the user who triggered this task.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

πŸ’‘ Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 6538f05cbf

ℹ️ About Codex in GitHub

Your team has set up Codex to 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 πŸ‘.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines +323 to +324
if #available(macOS 10.15.4, *) {
try? handle.close()

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Do not ignore close failures before committing journal

On macOS 14 this branch is always used, and try? handle.close() discards delayed write/close errors such as ENOSPC, quota, or I/O failures while flushing the file. flushState() then proceeds to rename the temp file and return true, so record(_:) can allow the sysctl write even though the journal state was not durably written, defeating the rollback guarantee. Please treat a thrown close as a failed flush and remove the temp file instead of committing it.

Useful? React with πŸ‘Β / πŸ‘Ž.

Comment on lines +321 to +322
let handle = FileHandle(fileDescriptor: fd, closeOnDealloc: true)
handle.write(data)

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Use the throwing FileHandle write API

When the temp journal write itself fails, for example because /var/run is out of space or returns an I/O error, this non-throwing FileHandle.write(_:) path does not report a Swift error to the surrounding catch the way the previous Data.write(to:) did. That can leave flushState() unable to return false cleanly for record(_:), either aborting the helper or missing the durable-write failure before the sysctl change. Please use the throwing write(contentsOf:) API and handle the error like the open/rename failures.

Useful? React with πŸ‘Β / πŸ‘Ž.

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.

1 participant