Benchmark RadarAI BENCHMARK PROFILE
PRWeaver
PRWeaver evaluates LLM-based code auditors against malicious pull requests across repository history, using 208 attacks and multiple renderings.
- Released
- 2026-08-03
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Addresses reliability of code auditing agents under adversarial conditions, informing deployment of such systems.
Motivation
LLM-based code auditors are increasingly integrated into pull-request (PR) workflows, yet their reliability against adversarial changes distributed across repository evolution remains poorly understood.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.