A security analysis of 117,854 AI agent skills revealed that a significant majority (82.3%) have never been graded for safety. Among the skills that were assessed, approximately 1 in 32 were found to be unsafe or have security concerns. The study also identified a new attack surface related to agent configuration and memory theft, highlighting that risks are concentrated in less popular, long-tail skills rather than widely used ones. AI
IMPACT Highlights critical security gaps in AI agent ecosystems, potentially slowing adoption until trust layers mature.
RANK_REASON Security analysis of AI agent skills with statistical findings. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
