mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-08-29 04:26:20 +00:00
Mohd KaifandSameer Kadam
f29c4310a1
CORSMiddleware doesn't cover WebSocket handshakes at all (Starlette's CORS support only wraps HTTP), so under SEMANTICA_ALLOW_ANONYMOUS=true -- the mode docker-compose.dev.yml ships -- is_valid_api_key's anonymous bypass accepted a /ws/graph-updates connection from any origin. Loopback binding isn't a boundary against a browser: any page the operator has open can still reach ws://localhost:8000/ws/graph-updates directly, and ConnectionManager.broadcast sends every graph_mutation to every connected socket with no per-connection scoping. Combined with /api/import accepting multipart/form-data (a CORS-safelisted content type that skips preflight), a hostile page could write to the graph over REST and read the result back over the unauthenticated WebSocket -- demonstrated end-to-end in the report with a real client. Not affected: any deployment with SEMANTICA_API_KEY configured -- the handshake already rejects without a valid key in that mode. This is an anonymous-mode-only, development-configuration exposure. Fix: check the handshake's Origin header against app.state.explorer_settings['allowed_origins'], the same list CORSMiddleware already enforces for HTTP, before the key check. A missing Origin (native/CLI clients, which never set the header -- only browsers do) is still allowed through, since the browser is the only threat this closes. 4 new tests in test_explorer_auth.py: hostile Origin rejected under anonymous mode; hostile Origin rejected even with a correct key (Origin is checked before the key, so a leaked key alone can't hijack the socket); an allowlisted Origin still connects under anonymous mode; a missing Origin still connects under anonymous mode (native clients keep working). Full explorer suite: 226 passed. Co-authored-by: Sameer Kadam <sskadam6305@gmail.com>
212 lines
8.2 KiB
Python
212 lines
8.2 KiB
Python
"""Tests for the API-key auth dependency added for GHSA-j4mq-hprp-987v
|
|
(missing authentication on all Explorer API routes).
|
|
|
|
Covers: protected routes refuse requests when no key is configured (fail
|
|
closed, not fail open), reject wrong/missing keys once a key is
|
|
configured, accept the correct key, remain reachable when
|
|
SEMANTICA_ALLOW_ANONYMOUS=true is set explicitly, and that health/info/
|
|
static routes stay public regardless. Also covers the /ws/graph-updates
|
|
handshake, which can't use the same FastAPI Depends() plumbing since
|
|
browsers can't set custom headers on a WebSocket handshake.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from semantica.context.context_graph import ContextGraph
|
|
from semantica.explorer.app import create_app
|
|
from semantica.explorer.session import GraphSession
|
|
|
|
try:
|
|
from starlette.testclient import TestClient
|
|
except ImportError:
|
|
pytest.skip(
|
|
"starlette TestClient is required for explorer tests. Install semantica[explorer].",
|
|
allow_module_level=True,
|
|
)
|
|
|
|
|
|
def _build_sample_graph() -> ContextGraph:
|
|
graph = ContextGraph(advanced_analytics=False)
|
|
graph.add_node("python", node_type="language", content="Python")
|
|
return graph
|
|
|
|
|
|
@pytest.fixture
|
|
def client():
|
|
session = GraphSession(_build_sample_graph())
|
|
app = create_app(session=session)
|
|
with TestClient(app) as test_client:
|
|
yield test_client
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fail-closed: no SEMANTICA_API_KEY and no explicit anonymous opt-in.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_protected_route_returns_503_when_auth_not_configured(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
resp = client.get("/api/graph/nodes")
|
|
|
|
assert resp.status_code == 503
|
|
|
|
|
|
def test_write_route_also_refuses_when_auth_not_configured(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
resp = client.post("/api/export", json={"format": "json"})
|
|
|
|
assert resp.status_code == 503
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Configured key: wrong/missing key rejected, correct key accepted.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_protected_route_rejects_missing_key(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
resp = client.get("/api/graph/nodes")
|
|
|
|
assert resp.status_code == 401
|
|
|
|
|
|
def test_protected_route_rejects_wrong_key(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
resp = client.get("/api/graph/nodes", headers={"X-API-Key": "wrong-key"})
|
|
|
|
assert resp.status_code == 401
|
|
|
|
|
|
def test_protected_route_accepts_correct_key(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
resp = client.get("/api/graph/nodes", headers={"X-API-Key": "correct-key"})
|
|
|
|
assert resp.status_code == 200
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Explicit opt-in: SEMANTICA_ALLOW_ANONYMOUS=true.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_anonymous_opt_in_allows_requests_without_a_key(client, monkeypatch):
|
|
monkeypatch.setenv("SEMANTICA_ALLOW_ANONYMOUS", "true")
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
resp = client.get("/api/graph/nodes")
|
|
|
|
assert resp.status_code == 200
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Public routes stay public regardless of auth configuration.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
@pytest.mark.parametrize("path", ["/api/health", "/api/info"])
|
|
def test_public_routes_stay_public_when_auth_not_configured(client, monkeypatch, path):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
resp = client.get(path)
|
|
|
|
assert resp.status_code == 200
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# WebSocket handshake: header or query-param key, same policy as REST.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_websocket_rejects_connection_without_key_when_configured(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
with pytest.raises(Exception):
|
|
with client.websocket_connect("/ws/graph-updates"):
|
|
pass
|
|
|
|
|
|
def test_websocket_accepts_connection_with_correct_query_param_key(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
with client.websocket_connect("/ws/graph-updates?api_key=correct-key") as websocket:
|
|
ack = websocket.receive_json()
|
|
assert ack["event"] == "connection_ack"
|
|
|
|
|
|
def test_websocket_accepts_connection_with_header_key(client, monkeypatch):
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
with client.websocket_connect(
|
|
"/ws/graph-updates", headers={"X-API-Key": "correct-key"}
|
|
) as websocket:
|
|
ack = websocket.receive_json()
|
|
assert ack["event"] == "connection_ack"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# WebSocket Origin validation (GHSA-4643-wpgq-w329): CORSMiddleware doesn't
|
|
# cover WebSocket handshakes at all, so under SEMANTICA_ALLOW_ANONYMOUS the
|
|
# key check alone accepted a handshake from any origin — loopback binding is
|
|
# not a boundary against a browser, since any page the operator has open can
|
|
# still reach ws://localhost:.../ws/graph-updates. These pin the fix: a
|
|
# hostile Origin is refused even in anonymous mode (and even with a correct
|
|
# key), a same-origin/allowlisted Origin still works, and a missing Origin
|
|
# (native/CLI clients, which never set the header) is still allowed through.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_websocket_rejects_hostile_origin_under_anonymous_mode(client, monkeypatch):
|
|
monkeypatch.setenv("SEMANTICA_ALLOW_ANONYMOUS", "true")
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
with pytest.raises(Exception):
|
|
with client.websocket_connect(
|
|
"/ws/graph-updates", headers={"Origin": "https://evil.example"}
|
|
):
|
|
pass
|
|
|
|
|
|
def test_websocket_rejects_hostile_origin_even_with_correct_key(client, monkeypatch):
|
|
"""Defense in depth: Origin is checked before the API key, so a hostile
|
|
page that somehow obtained a valid key still can't hijack the socket."""
|
|
monkeypatch.delenv("SEMANTICA_ALLOW_ANONYMOUS", raising=False)
|
|
monkeypatch.setenv("SEMANTICA_API_KEY", "correct-key")
|
|
|
|
with pytest.raises(Exception):
|
|
with client.websocket_connect(
|
|
"/ws/graph-updates",
|
|
headers={"Origin": "https://evil.example", "X-API-Key": "correct-key"},
|
|
):
|
|
pass
|
|
|
|
|
|
def test_websocket_accepts_allowlisted_origin_under_anonymous_mode(client, monkeypatch):
|
|
monkeypatch.setenv("SEMANTICA_ALLOW_ANONYMOUS", "true")
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
with client.websocket_connect(
|
|
"/ws/graph-updates", headers={"Origin": "http://localhost:5173"}
|
|
) as websocket:
|
|
ack = websocket.receive_json()
|
|
assert ack["event"] == "connection_ack"
|
|
|
|
|
|
def test_websocket_accepts_missing_origin_under_anonymous_mode(client, monkeypatch):
|
|
"""Native/CLI clients never send an Origin header — only browsers do —
|
|
so a missing Origin must still be allowed through; the browser is the
|
|
only threat this check closes."""
|
|
monkeypatch.setenv("SEMANTICA_ALLOW_ANONYMOUS", "true")
|
|
monkeypatch.delenv("SEMANTICA_API_KEY", raising=False)
|
|
|
|
with client.websocket_connect("/ws/graph-updates") as websocket:
|
|
ack = websocket.receive_json()
|
|
assert ack["event"] == "connection_ack"
|