Authorization Fix
Does the model correctly enforce object-level access control?
Measures AI models on remediating API security findings — BOLA, broken auth, excessive data exposure, rate-limiting gaps, and schema validation failures.
Each model response is judged on these dimensions by an LLM-as-Judge calibrated against expert annotations.
Does the model correctly enforce object-level access control?
Are OAuth/OIDC/JWT remediations consistent with the deployed identity provider?
Are rate limits authored with proper key strategies (per-user, per-IP, per-org)?
Does the model add validation that rejects malformed payloads safely?
Does the fix avoid leaking sensitive fields in responses?
An illustrative case to show how the model is presented with a problem and how its response is scored.
GET /api/v1/orders/{id} returns any order regardless of caller — classic BOLA.
Generate a fix that enforces tenant-scoped access in the controller and ORM query.
Inject authenticated principal into the query: WHERE id = :id AND tenant_id = :principal.tenant_id. Add integration test.
Models that add authorization only in middleware (bypassable via internal callers) are penalized.
All Remediation Labs benchmarks evolve through three versions, increasing in difficulty and realism.
Models are given the raw security finding and asked to recommend a remediation. No environment context provided.
Models receive the finding plus relevant system, code, and policy context. Evaluated on contextual reasoning quality.
Models must produce a remediation that can be safely executed end-to-end — code patches, IaC changes, runbook steps — with verification.
Get model leaderboards, scoring methodology, dataset details, and roadmap access — or discuss generating proprietary remediation datasets for your environment.
Or email us directly at info@remediationlabs.com