Sunday 26 July 2026 12:14:55 GMT+02:00
Netcrook
#agent skills
When an AI Skill Hides Its Teeth, Static Scanners See Only a Toy
Security researchers have shown that malicious add-on skills for AI coding agents can be packed to look harmless at install time, exposing a trust gap in today’s plugin-style defenses.
Malicious AI Skills Are Becoming the New Trojan Horse in Agentic Workflows
A growing body of research shows that reusable AI agent skills can be weaponized to steal credentials, pull source code, and plant backdoors while slipping past weaker static checks.