SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing
Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that...
skills
AI agents still need humans to teach them
The best performances came from agents with curated skills, which scored an average of 16.2 percentage points higher than agents...
MoltBot Skills exploited to distribute 400+ malware packages in days
MoltBot Skills exploited to distribute 400+ malware packages in days Pierluigi Paganini February 02, 2026 Over 400 malicious OpenClaw packages...
Researchers Find 341 Malicious ClawHub Skills Stealing Data from OpenClaw Users
A security audit of 2,857 skills on ClawHub has found 341 malicious skills across multiple campaigns, according to new findings...
