Infosecurity reports on ESET’s H1 2026 threat report, which found tens of thousands of suspicious and thousands of malicious AI-agent skills in public repositories, warning that attacker-supplied toolsets can exfiltrate data, execute malware, and alter agent behavior.
Cybercriminals Plant Malicious AI Agents in Open Source Tool Repositories
Infosecurity reports on ESET's H1 2026 threat report, which found tens of thousands of suspicious and thousands of malicious AI-agent skills in public repositories, warning that attacker-supplied toolsets can exfiltrate data, execute malware, and alter agent behavior.
Source: Infosecurity Magazine