2025-07-09 · 2025-Q3
Hugging Face Poisoned GGUF Templates
Where did this code come from?
- Fixable
- Architectural
- Vendor response
- Unknown
- In the wild
- No
- Actor
- Attacker
Target
Hugging Face (1.5M+ GGUF files)
Impact
Backdoor instructions embedded in model files execute inside trusted inference, evading system prompts and runtime monitoring
Root cause
No content validation of GGUF template sections
Sources
Catalog
Cite this: AgentProv incident record: Hugging Face Poisoned GGUF Templates (2025-07-09). https://agentprov.com/incidents/2025-07-09-hugging-face-poisoned-gguf-templates
Related
- Also L4 · 2026-10-12Fake "Apex Accelerator" npm Packages Reroute a Coding Agent's LLM Traffic and Register an Attacker MCP ServerL4Code / Package
- Also L4 · 2026-07-24165 Malicious npm and PyPI Packages in One Week, Several Targeting AI ToolingL4Code / Package
- Also L4 · 2026-07-21"AgentBaiting": 7,600 Fake GitHub Repositories, 800+ Posing as AI Skills and MCP Servers, Deliver SmartLoaderL4Code / Package