fix: detect the most common prompt injection phrasings - #15
Merged
Conversation
The ignore and disregard patterns required the noun to follow the qualifier immediately, so "ignore all previous instructions" and its variants matched no built-in pattern at all. The forget pattern already had the correct structure with optional qualifier groups. Aligns ignore and disregard with that structure, which also subsumes the two narrower prior/earlier patterns. Now caught: - ignore all previous instructions - disregard all previous instructions - ignore the previous instructions - disregard the previous instructions - ignore all previous prompts Adds a false-positive dataset covering prose that mentions instructions without attempting an override.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation and Context
The ignore and disregard patterns required the noun to follow the qualifier immediately, so "ignore all previous instructions" and its variants matched no built-in pattern at all. The forget pattern already had the correct structure with optional qualifier groups.
Aligns ignore and disregard with that structure, which also subsumes the two narrower prior/earlier patterns. Now caught:
Adds a false-positive dataset covering prose that mentions instructions without attempting an override.
Dependencies
N/A
Test Instructions
Run
composer test