12:34
2026-09-08
dev.to
ai-safety
We Benchmarked 5 OpenClaw Skill Scanners. Recall Went From 8% to 95%.
A benchmark of five OpenClaw skill scanners found that agent-based auditing dramatically outperforms static analysis, improving recall from 8% to 95% on a test set of 60 skills. The Trent AI team's Op…