sanitize datasource_description in tool descriptions; validate document_id#21
Open
lwsinclair wants to merge 1 commit intomainfrom
Open
sanitize datasource_description in tool descriptions; validate document_id#21lwsinclair wants to merge 1 commit intomainfrom
lwsinclair wants to merge 1 commit intomainfrom
Conversation
thuong-nguyen-ea
approved these changes
Apr 20, 2026
thuong-nguyen-ea
left a comment
thuong-nguyen-ea
left a comment
There was a problem hiding this comment.
LGTM — datasource_description sanitization + document_id validation
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The datasource_description returned from the API was appended directly to every tool description the MCP client sees. If any field writable by a non-owner ends up there, it becomes LLM instructions. Now stripped of control chars, truncated, and wrapped in an untrusted-data marker.
document_id taken from resource URIs was substituted into URL paths unchecked — validated with a hex/dash regex.