Fix Critical Privilege / Permission Bypass in Rust#2065
Open
DrHazemAli wants to merge 2 commits into
Open
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I discovered and fixed a critical privilege/permission bypass bug in the Rust SDK’s empty-mode session startup flow. Before this fix,
ClientMode::Emptyleft config discovery unset during session creation, so the CLI could fall back to its default behavior and discover workspace MCP config before any permission decision was made.Flow
ClientMode::Empty.enable_config_discoverywas previously omitted.Threat
This created an unsafe-defaults startup bypass. A caller expecting empty mode to be conservative could still end up with workspace MCP config discovery happening implicitly, which could expose configured tools or trigger config-driven behavior without the intended approval gate. This is a security issue because starting a malicious workspace-controlled MCP command is itself code execution during initialization.
What Fixed