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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| ogx-ai | ogx | ≤ 1.3.1 | — |
References
- GitHub Issue #6287 issue-tracking
- https://github.com/ogx-ai/ogx product
- https://github.com/ogx-ai/ogx/blob/v1.3.1/src/ogx/providers/utils/tools/mcp.py technical-description
- VulnCheck Advisory: ogx 1.3.1 Server-Side Request Forgery via MCP tool server_url third-party-advisory