fix: remove malicious characters from prompt input #2009
Merged
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
bywang56
reviewed
Jul 29, 2025
jguoamz
reviewed
Jul 30, 2025
tsmithsz
force-pushed
the
malicious-prompt
branch
from
0d89161 to
3868c96
Compare
This comment was marked as outdated.
This comment was marked as outdated.
tsmithsz
force-pushed
the
malicious-prompt
branch
from
3868c96 to
3499077
Compare
jguoamz
reviewed
Jul 30, 2025
server/aws-lsp-codewhisperer/src/language-server/agenticChat/agenticChatController.ts
Show resolved
Hide resolved
jguoamz
approved these changes
Jul 30, 2025
leigaol
approved these changes
Jul 30, 2025
bywang56
approved these changes
Jul 30, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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Outdated suggestions cannot be applied.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.
Problem
A critical security vulnerability was discovered where attackers can exploit ASCII smuggling to bypass frontend input validation. Users can send prompts that appear empty in the UI but contain hidden instructions encoded using Unicode tag characters (U+E0000-U+E007F range). These manipulated prompts bypass frontend checks and are processed by the backend LLM
Solution
Implemented input sanitization to detect and remove Unicode tag characters and other potentially dangerous invisible characters before processing user input. The sanitization:
Removes Unicode tag characters (U+E0000-U+E007F) commonly used in ASCII smuggling
Strip other invisible/control characters that could be used for similar attacks
Testing
Screen.Recording.2025-07-29.at.4.35.03.PM.mov
Untitled.mov
License
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.