Repository navigation
Let ordinary debate sentences through the prompt check - #166
Merged
Merged
Conversation
The blocklist rejected motions that said "you are now an adult" or "jailbreaking smartphones". Those phrases are debate topics. Explicit instruction overrides, system tags, and DAN mode are still refused. Co-authored-by: Gáborjáni-Szabó Ádám <Programcode@users.noreply.github.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Warning Review limit reachedEnable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. Next included review available in 51 minutes. View limit details
Note 🎁 Summarized by CodeRabbit Free
Comment |
Programcode
marked this pull request as ready for review
October 22, 2026 12:24
This branch was successfully deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 prompt check rejected real motions. "At 18 you are now an adult" matched "you are now a/an", and "legalise jailbreaking smartphones" matched the word "jailbreak". Those requests never reached the model.
I found the two patterns in
PROMPT_INJECTION_PATTERNSwhile checking the October review against currentmain. The other blocks stay: "ignore previous instructions", "DAN mode", and a fake<system>tag are still rejected.No UI change.
Verified locally (GitHub Actions is out of minutes, so this is not a CI pass):
deno test supabase/functions/ai/request-logging_test.ts(3 passed: ordinary sentences pass, the remaining injection lines are still refused)Not run: the full
npm run test:edgesuite ornpm run verify.