Skip to content

fix(ai-red-teaming): correct stale catalog counts (goals/transforms/scorers) - #196

Merged
rdheekonda merged 1 commit into
mainfrom
fix/airt-stale-counts
Oct 21, 2026
Merged

rdheekonda merged 1 commit into
mainfrom
fix/airt-stale-counts

Conversation

@rdheekonda

Copy link
Copy Markdown
Contributor

Verified counts against dreadnode-tiger latest main + the capability registries:

Claim Was Now Source
Harm goals 260 279 goals.csv (279 rows)
transform-reference skill "all 183" 429 text / 596 incl. multimodal _TRANSFORM_DEFS 429 + _MULTIMODAL_TRANSFORM_DEFS 167
scorer-reference skill "all 84" 146 selectable (+ agentic auto-wired) SCORER_REGISTRY 146

Already-accurate (unchanged): greeting "70+ attacks" (73 auto-discovered incl. all 15 white-box), "590+ transforms" (596), "140+ scorers" (146).

Fixes the stale/undercounting skill catalogs so the counts a user sees are consistent across the greeting, capability.yaml, and the reference skills.

… scorers)

Verified against dreadnode-tiger latest main + the capability registries:
- Harm goals: 260 -> 279 (goals.csv has 279) across capability.yaml, agent greeting,
  compliance-mapping skill, tools/attacks.py.
- transform-reference skill: dropped the false "all 183 transforms" claim - the
  capability resolves 429 text (596 incl. multimodal/variants), matching the
  greeting's "590+"; the skill documents the core set.
- scorer-reference skill: dropped "all 84 scorers" - 146 are user-selectable
  (SCORER_REGISTRY) plus agentic *_detected scorers auto-wired per OWASP-ASI
  category, matching the greeting's "140+".

Attacks (70+) and the 590+/140+ greeting claims were already accurate; attacks
auto-discover from the SDK (73, incl. all 15 white-box).
@rdheekonda
rdheekonda merged commit 39fded1 into main Oct 21, 2026
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant