mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-06 02:48:13 +00:00
df62dd8768
The OAuth discovery code in mcp_server_manager followed two
attacker-influenceable URLs without validation: the
``resource_metadata`` URL parsed out of a ``WWW-Authenticate``
challenge, and the ``authorization_servers[0]`` field of the
PRM JSON returned by the resource server. A malicious MCP server
could point those at a cloud-instance-metadata service, an internal
admin panel, or a loopback debug endpoint and the proxy would issue
a blind GET on its behalf.
Add ``_is_safe_metadata_url(url, server_url)`` and gate both follow-
up fetch sites on it. A URL is allowed when:
- it shares scheme + host + port with ``server_url`` (well-known
endpoints constructed from the admin's URL, and PRM published at
the resource server itself per RFC 9728 §3.3), or
- it resolves to publicly-routable IPs only (covers federated
authorization servers — Azure Entra, Google, Okta, GitHub —
hosted cross-origin from the resource server).
URLs that resolve to private / loopback / link-local / cloud-metadata
addresses, or that don't resolve at all, are rejected. ``http`` and
``https`` are the only schemes accepted. The IP block list is
provided by the existing ``_is_blocked_ip`` helper from
``litellm_core_utils.url_utils`` so the policy stays consistent with
the rest of the proxy.
The guard does not protect against active DNS rebinding between
this resolution and the subsequent httpx GET — the same-authority
pin remains the primary mitigation; the IP check is defence in
depth. The surface only triggers on config load / add-server, not
per request, so the synchronous ``getaddrinfo`` is acceptable.
Threads ``server_url`` through ``_fetch_oauth_metadata_from_resource``,
``_fetch_authorization_server_metadata``, and
``_fetch_single_authorization_server_metadata``. Existing tests for
those helpers updated for the new signature; new
``TestOAuthDiscoverySSRFGuard`` covers same-authority allow,
private-IP rejection across IPv4 and IPv6, multi-A-record dual-
stack rejection, unresolvable hosts, non-http schemes, and
end-to-end "no network call when guard denies".
|
||
|---|---|---|
| .. | ||
| auth | ||
| guardrail_translation | ||
| test_byok_oauth_endpoints.py | ||
| test_discoverable_endpoints.py | ||
| test_is_tool_name_prefixed.py | ||
| test_jwt_mcp_enforcement.py | ||
| test_jwt_mcp_simple.py | ||
| test_mcp_cost_calculator.py | ||
| test_mcp_custom_fields.py | ||
| test_mcp_debug.py | ||
| test_mcp_discovery.py | ||
| test_mcp_hook_extra_headers.py | ||
| test_mcp_metadata_preservation.py | ||
| test_mcp_server.py | ||
| test_mcp_server_manager.py | ||
| test_mcp_sigv4_auth.py | ||
| test_mcp_stale_session.py | ||
| test_mcp_toolset_scope.py | ||
| test_oauth2_token_cache.py | ||
| test_openapi_to_mcp_generator.py | ||
| test_rest_endpoints.py | ||
| test_semantic_tool_filter.py | ||
| test_short_mcp_tool_prefix.py | ||
| test_ui_session_utils.py | ||