AgentBaiting Campaign Uses 800 Fake AI Skills and MCP Servers to Deliver SmartLoader Malware

Cybersecuritynews •Tushar Subhra Dutta • July 21, 2026

Malware operators are increasingly using tools built to extend artificial intelligence as a delivery route. A newly documented campaign called AgentBaiting uses fraudulent AI Skills and Model Context Protocol, or MCP, servers to distribute SmartLoader malware through trusted-looking GitHub projects and public capability catalogs. The operation turns a routine for an AI integration into […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

AgentBaiting Campaign Exploits AI Skills to Distribute SmartLoader Malware The AgentBaiting campaign has emerged as a significant threat, utilizing 800 fake AI Skills and Model Context Protocol (MCP) servers to deliver SmartLoader malware. This operation leverages trusted GitHub projects and public capability catalogs to disguise malicious activities. The malware delivery method exploits the growing trust in AI integrations, turning them into vectors for cyberattacks. The campaign is notable for its scale, with 7,600 repositories involved in the operation. Affected systems include those relying on AI capabilities and MCP workflows. The current status of the campaign indicates ongoing exploitation, with no immediate resolution reported. Security professionals are advised to remain vigilant against this evolving threat. 2 sources 65

Extracted Entities

AgentBaiting Campaign Uses 800 Fake AI Skills and MCP Servers to Deliver SmartLoader Malware

The full story

Extracted Entities

Attack Types (2)

Campaigns (2)

MITRE ATT&CK (1)

Platforms (1)