CyberRota Analysis
AI-GeneratedOllama is vulnerable due to inadequate validation of redirect destinations when pulling tensor-layer models, enabling unauthenticated attackers to redirect blob downloads to arbitrary hosts. This flaw allows attackers to serve malicious tensor-layer manifests, potentially leading to unauthorized access to internal resources, including sensitive cloud metadata endpoints. Organizations utilizing Ollama for model management should prioritize patching this vulnerability to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to redirect blob downloads to arbitrary hosts. An attacker can control a registry, serve a malicious tensor-layer manifest, and cause the server to issue GET requests to internal hosts including cloud metadata endpoints.