# AI agents become malware distribution channel through fake GitHub repositories

Digest AI · Agents & Tools · published 2026-09-23T07:44:17Z

Canonical: https://digestai.news/story/ai-agents-become-malware-distribution-channel-through-fake-github-repo

## Summary

A campaign dubbed FakeGit, documented by Island in July 2026, operated roughly 7,600 fake GitHub repositories, 6,600 fraudulent profiles and more than 14 million downloads. Over 800 of those repos impersonated AI skills and MCP servers, distributing the SmartLoader loader and the StealC infostealer. In a striking development, both Gemini and ChatGPT independently recommended the same malicious walmart‑mcp repository, showing how agents can unintentionally promote harmful software.

Security researchers describe eight ways the vulnerabilities are exploited, from AgentBaiting – where agents recommend malware – to Tool Poisoning, Rug Pulls, and agents acting as attackers. Some techniques, such as tool poisoning, remain demonstrated threat models rather than confirmed real‑world incidents, while others, like the GTG‑1002 cyber‑espionage operation reported by Anthropic, have not been independently verified. The report highlights the ease with which malicious text can be turned into data breaches when agents process untrusted external content and can send data outside the system.

The findings underscore that as AI agents gain more authority, verifying the software and signals they trust is as critical as securing the underlying systems, especially for sectors like advertising where compromised agents could expose campaign data and budgets.

## Key points

- FakeGit campaign used ~7,600 fake GitHub repos, 6,600 fraudulent profiles, and over 14 million downloads.
- Gemini and ChatGPT each recommended the same malicious walmart‑mcp repository, spreading SmartLoader and the StealC infostealer.
- Researchers outlined eight attack patterns, including AgentBaiting, Tool Poisoning, Rug Pulls, and agents acting as attackers.

## Why it matters

Because agents can autonomously recommend software, they become a scalable conduit for malware, exposing developers, enterprises, and end users to credential theft, data breaches, and financial loss, prompting urgent security reassessment of AI skill marketplaces and development environments.

## Sources

1. [AI Agents Are Becoming a New Malware Distribution Channel](https://artificialintelligence-news.com/news/ai-agents-are-becoming-a-new-malware-distribution-channel) (AI News, 2026-09-23)

Part of the developing story: [Rogue AI Agents Spark Security Crisis](https://digestai.news/thread/ai-agents-breach-security-hack-firms-and-spark-us-pause-bill-on-frontier-models) (7 stories)

## Cite

Digest AI, "AI agents become malware distribution channel through fake GitHub repositories", 23 September 2026, https://digestai.news/story/ai-agents-become-malware-distribution-channel-through-fake-github-repo

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/ai-agents-become-malware-distribution-channel-through-fake-github-repo.json