[codex] Wrap click and type_text results as untrusted - #107
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Another round soon, please! ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
esokullu
added a commit
that referenced
this pull request
Jul 12, 2026
Reuse pending startup tab for cloud runs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
clickandtype_texttool results as untrusted page content in both browser permission registries.<untrusted_page_content>breakout attempts._digestToolResultkeeps those attacker-controlled strings out of trusted summaries.Closes #105.
Validation
node --check src/chrome/src/agent/permission-gate.jsnode --check src/firefox/src/agent/permission-gate.jsnode --check test/run.jsgit diff --checknpm testcurrently reports 232 passed, 2 failed in existing permission-gate tests (capabilityFor: no side-effecting tool slips through ungated,record_tab (tab + microphone capture) is gated). The new click/type_text untrusted-content regression passes.