Extra security for avoiding agent to read/write outside allowed paths - #486
Open
lewcpe wants to merge 3 commits into
Open
Extra security for avoiding agent to read/write outside allowed paths#486lewcpe wants to merge 3 commits into
lewcpe wants to merge 3 commits into
Conversation
added 2 commits
August 10, 2026 11:06
aniketshukla1
suggested changes
Aug 10, 2026
aniketshukla1
left a comment
aniketshukla1
left a comment
There was a problem hiding this comment.
Blocking security issue documented inline: shell parameter expansion still bypasses the new workspace-root enforcement in AUTO mode.
…gle-quote awareness
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I found that some LLMs tend to find workarounds to read or write files outside their designated paths. While static blocking in permissions.py can't offer an absolute security guarantee, adding extra detection along with a system prompt instructing the agent not to bypass limits works well enough.