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.

OGX (formerly Llama Stack), at commit fbe8e0f, contains an unauthenticated Server-Side Request Forgery (SSRF) vulnerability in its OpenAI-compatible POST /v1/responses endpoint. MCP tool definitions accept a server_url parameter that is fetched server-side without any destination validation, as the existing validate_url_not_private() guard is not applied to this parameter. In the default starter configuration, which runs without authentication, a remote unauthenticated attacker can cause the server to connect to arbitrary internal addresses, including cloud metadata endpoints such as http://169.254.169.254/. The attacker can also forward attacker-supplied headers and bearer tokens to those internal destinations, enabling credential theft and internal network reconnaissance. This vulnerability poses a significant risk in cloud-hosted deployments where metadata endpoints expose sensitive credentials. A fix would require applying the existing URL validation guard to the server_url parameter as well.