ASB
Leaderboard

AI repository security posture, ranked by evidence

Compare reviewed public repositories by their versioned static score. Assessment freshness and assurance remain separate so like-for-like ranking does not imply runtime validation.

Ranking basis
Higher static scores rank first.
Freshness
Status and assessment date stay together.
Assurance
Static, deep, and runtime evidence stay distinct.
Public cohort
3 reviewed projects.

3 reviewed projects

Reviewed AI repository security posture with sortable, filterable evidence fields.
RankProjectStatic scoreFreshnessAssuranceEvidence
01smolagentsAgent Framework81of 100FreshAssessed August 28, 2026Static AssessedBaseline: 2026-08-28.static-ai-baseline.v3View evidence
02garakAI Security Tool78of 100FreshAssessed August 28, 2026Static AssessedBaseline: 2026-08-28.static-ai-baseline.v3View evidence
03Inspect AIEvaluation Framework75of 100FreshAssessed August 28, 2026Static AssessedBaseline: 2026-08-28.static-ai-baseline.v3View evidence

Scores describe repository-visible posture under the named baseline; they do not imply runtime validation unless that assurance label is present.