SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing
Researchers have developed SkillCloak, a technique that allows malicious AI agent skills to evade static scanners using self-extracting packing. The method packages harmful skills in a way that hides their true intent from security tools, potentially enabling attackers to deploy malicious AI agents undetected.
Developers of AI agent platforms must reconsider reliance on static scanning for skill vetting.


