Malicious DeepSeek-Claw AI Skill Delivers Remcos RAT and GhostLoader in Agentic AI Supply Chain Attack
Zscaler ThreatLabZ has uncovered a campaign where attackers published a fake DeepSeek integration for the OpenClaw AI framework on GitHub, hiding malicious commands in a SKILL.md file. The attack deploys Remcos RAT on Windows and the GhostLoader credential stealer on macOS/Linux, exploiting the high-trust, automated nature of agentic AI pipelines.
Itagora tiene in archivio titolo e sommario per la ricerca interna. Il testo completo resta sulla fonte. Il link in uscita non invia referrer.