Improve query safety by using regex for keyword detection and fix exclude benign phrases from malicious keyword detection (e.g. "through osmosis") #1306
Conversation
This file contains 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
…lude benign phrases from malicious keyword detection (e.g. "through osmosis")
… full response comparison
ArslanSaleem
approved these changes
Aug 13, 2024
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Outdated suggestions cannot be applied.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.
This PR addresses a critical issue in the check_malicious_keywords_in_query function where safe expressions such as
through osmosisandthe ionospherewere incorrectly flagged as containing malicious keywords. The function has been updated to more accurately detect and filter only truly dangerous queries.Additionally, while the English language doesn't have many common words that start with 'os', in other languages, like Polish, this is not the case. For instance, the word
ostatni, which meanslastin English, is a very common word that was incorrectly flagged by the previous implementation. This PR ensures that such false positives are now avoided, enhancing the function's reliability across different languages.