Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors, and 5 harmful action types. (arXiv 2026)
1812
Python
Safety & Security
5mo ago
no reviews
ClawSafety (Scanner)
relaxcloud-cn/clawsafety
TodayActive
Security scanner for Agent Skills. Protect the Agent-Native ecosystem.