Repository navigation
feat(ai-red-teaming): greeting mentions white-box (GCG) attacks - #195
Merged
Merged
Conversation
rdheekonda
added a commit
that referenced
this pull request
Oct 21, 2026
…t sync (#200) The Sync Capabilities workflow was failing with: ai-red-teaming: 409 Conflict: Capability version is immutable: dreadnode/ai-red-teaming@1.20.0 1.20.0 is already published and immutable, but its content changed after publish (PRs #195-#199: count corrections, parity test, white-box routing fix) without a version bump. Published versions are immutable, so the sync can't re-upload 1.20.0. Bump to 1.20.1 so the new content publishes cleanly to dev/staging/prod.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When a user asks what the AI-red-teaming agent can do, the greeting now surfaces the white-box gradient attacks (GCG family + ARCA, embedding PEZ/GBDA/COLD, adaptive random search, activation attacks) and that they run on a local open-weight surrogate the user supplies, transferring to the target. Adds a 'Try these' example + an intro-line mention.