CyberRota Analysis
AI-GeneratedThe vulnerability allows unauthenticated remote attackers to exploit the OpenAI-compatible POST /v1/responses endpoint in OGX, enabling server-side request forgery (SSRF) that can access arbitrary internal addresses, including sensitive cloud metadata endpoints. This could lead to unauthorized data exposure or further attacks within the network. Organizations using OGX, particularly those with default configurations and no authentication, should prioritize patching this vulnerability to mitigate potential risks.
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
OGX (formerly Llama Stack, affected at commit fbe8e0f) contains an unauthenticated server-side request forgery vulnerability in the OpenAI-compatible POST /v1/responses endpoint. MCP tool definitions accept a server_url parameter (along with headers and authorization values) that is fetched server-side without destination validation; the existing validate_url_not_private() guard used for other URL inputs is not applied to server_url. On the default starter configuration, which runs without authentication, a remote unauthenticated attacker can cause the server to open connections to arbitrary internal addresses (including cloud metadata endpoints such as http://169.254.169.254/) and forward attacker-supplied headers and bearer tokens to those destinations.