{ads}

SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing



July 6, 2026 at 12:03PM

Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong University of Science and Technology. Their strongest trick slipped past every scanner tested more than 90% of the time, and the same team built a runtime checker that catches most of the

from The Hacker News https://ift.tt/SM9Wliv

0 Response to "SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing"

Post a Comment

Article Top Ads

Central Ads Article 1

Middle Ads Article 2

Article Bottom Ads