docs(ai-red-teaming): unify capability counts (590+ transforms, 70+ attacks, 140+ scorers) - #115
Merged
Merged
Conversation
Replace stale/inconsistent figures (45 attacks, 500+ transforms, extensive scorer catalog) with verified floors: 70+ attack strategies covering traditional ML and generative AI, 590+ transforms, 140+ scorers, 260 goals.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The
ai-red-teamingcapability advertised stale, self-inconsistent counts (agent.md: "45 attack algorithms (41 LLM + 4 adversarial ML samplers), 500+ transforms, an extensive scorer catalog"; capability.yaml: "500+ transforms"). This aligns them with the verifiedorigin/mainSDK registries and the matching dreadnode-tiger docs PR.Verified figures (SDK origin/main)
dreadnode.scorers.__all__.Changes
agents/ai-red-teaming-agent.md— description block, Attack Types intro (line 208), Transform Catalog note (line 244)capability.yaml— capability descriptionNot in this PR (flagged)
skills/transform-reference("all 183 transforms") andskills/scorer-reference("all 84 scorers") are literal enumerated catalogs — they need regeneration against the current SDK, handled separately so headline and list stay consistent.skills/compliance-mappinghas granular per-category counts ("12 attack algorithms", "200+ transforms") that also need a pass.Test plan