analiza aiqbench

This integration embeds Tencent's AI-Infra-Guard (AIG) into ClawScan to automate security reviews for skills and plugins on the ClawHub platform, utilizing a dual-scanner approach with an AI judge for final assessment. The system leverages benchmark testing against SkillTrustBench to validate detection accuracy across nine specific risk categories, including instruction hijacking and insecure dependencies. By preserving diverse scanner perspectives within a feedback loop, this setup aims to reduce false positives and improve the reliability of automated vulnerability identification in AI-driven development environments.