Skip to content
Forest Global Training Partners
Home Services AI Governance AI Risk Encyclopedia Contact Us
AI Risk Encyclopedia AI Use CasesAI RisksAI Hallucinations Topics Entities Sources
  1. Home
  2. AI Risks
  3. GPT-Proxy Backdoor in npm and PyPI turns Servers into…

AI Risks April 22, 2026 · Aikido Security

GPT-Proxy Backdoor in npm and PyPI turns Servers into Chinese LLM Relays

Running proxy servers on compromised machines is a recurring behavior in the Chinese threat landscape, driven in part by restrictions imposed by the ...

Read the original at Aikido Security ↗

Topics
China & GeopoliticsChatbots & LLMs
Mentions
ChinaGPTOpenAI
Tracked via
“chinese ai threat”

Related articles

  • Chinese hacker used DeepSeek to launch autonomous cyberattacks on vulnerable servers AI Risks · Aug 04, 2026
  • UltralyticsAILibrary Compromised: Cryptocurrency Miner Found in PyPI Versions AI Risks · Dec 07, 2024
  • Chinese hackers breached North American research institutions via REDCap servers AI Risks · Jun 17, 2026
  • This Week in AI (May 10-16): Chinese LLM Takes Coding SOTA; Anthropic Overtakes OpenAI ... AI Risks · May 18, 2026
  • 5 reasons to not miss Sonatype at RSAC 2025 AI Risks · Apr 19, 2025
  • Chinese Threat Actors Operated 18,000 Active C2 Servers Across Global Hosting Providers AI Risks · Jan 17, 2026

Shares players with

  • What is GLM 5.2? The new Chinese AI model that's rivalling Anthropic | Euronews
  • Did China's AI Save Hugging Face From Disaster After Open AI Hack? - Forbes
  • A New Trick Reveals AI Models' Inner Thoughts | WIRED
  • Chinese AI model GLM-5.3 shows advanced bug-finding capabilities | brief | SC Media
  • OpenAI Cuts GPT-5.6 Sol Prices For Developers: How Much Cheaper Is Its AI Model Now?
  • OpenAI's GPT-6 may lead to robotics breakthrough as soon as next year: Unitree founder

AI Risk Encyclopedia is a curated research index from Forest Global Training Partners. Articles belong to their publishers; we link to and summarize them.

Contact