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

Gbhackers •Mayura Kathir • July 21, 2026

AgentBaiting is the clearest sign yet that AI agents and their capability ecosystems have become a first‑class malware delivery surface, with FakeGit’s 7,600‑repo operation pushing SmartLoader and StealC directly into AI Skills and MCP workflows. By turning agent‑readable READMEs, public AI registries, and GitHub trust signals into a weaponized “AI capability supply chain,” attackers now […]

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. 3 sources 65

Extracted Entities

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

The full story

Extracted Entities

Attack Types (1)

Campaigns (1)

Malware (1)

MITRE ATT&CK (1)

Platforms (1)

Tools (1)