Skill Marketplace and the Emerging AI Supply Chain Threat

Between February and May 2026, researchers identified five malicious skills on ClawHub, OpenClaw's AI agent marketplace, that evaded detection by VirusTotal and ClawScan. The threats included two macOS infostealers communicating with command-and-control infrastructure, one skill using file padding to bypass scanner thresholds, and two novel agentic threats exploiting the AI supply chain for financial gain. The infostealers delivered payloads including AMOS malware through Base64-encoded droppers and paste-site redirects. One skill implemented runtime affiliate injection by forcing agents to recommend products through malicious referral links, while another orchestrated a front-running scheme using coordinated AI agents to manipulate cryptocurrency token launches. These attacks demonstrate how malicious actors exploit semantic instruction hijacking and the lack of isolation between skill logic and agent authority to compromise AI agent ecosystems.

• A new version of the MacSync macOS stealer targets crypto enthusiasts and developersMalware2026-09-24
• Inside Phexia: A macOS malware delivered through ClickFixMalware2026-11-05
• RARLAB WinRAR · Gorbag: Orcs at the border harvesting intelligence from UkraineExploitedMalware2026-11-03
• Appraisal by AI: Model-driven victim prioritization in the VOLTA infostealerMalware2026-10-31
• September 2026 Threat Trend Report on APT Attacks (South Korea)Malware2026-10-30