[security] Close post-#227 control-surface and fetcher gaps

PR #227 hardened most Wormhole/Infonet control surfaces behind
require_local_operator and made the CrowdThreat fetcher opt-in. An
audit of the codebase against that PR's stated goals turned up four
classes of gap that the original change missed:

1. Two operator-only endpoints were left unprotected:
   - POST /api/wormhole/join: calls bootstrap_wormhole_identity() and
     flips the node into Tor mode, exactly the surface #227 hardened
     on /api/wormhole/identity/bootstrap.
   - POST /api/sigint/transmit: relays APRS-IS packets over radio
     using operator-supplied credentials. Anything that reached the
     API could transmit on the operator's authority.

   Both now require_local_operator. test_control_surface_auth.py
   extended with regression coverage for both.

2. Five third-party fetchers were still default-on, phoning home to
   politically/commercially sensitive upstreams on every poll cycle:
   - fimi.py            -> euvsdisinfo.eu        -> FIMI_ENABLED
   - prediction_markets -> Polymarket + Kalshi   -> PREDICTION_MARKETS_ENABLED
   - financial.py       -> Finnhub / yfinance    -> FINANCIAL_ENABLED or FINNHUB_API_KEY
   - nuforc_enrichment  -> huggingface.co        -> NUFORC_ENABLED
   - news.py            -> configured RSS feeds  -> NEWS_ENABLED (default on, kill switch)

   Same CrowdThreat-style pattern: explicit env-var opt-in, empty
   the data slot and mark_fresh when disabled. New regression test
   file test_third_party_fetchers_opt_in.py asserts each fetcher's
   network entry point is not called when its gate is off.

3. The outbound User-Agent leaked both the operator's personal email
   and a fork-specific GitHub URL on every fetcher request. Consolidated
   to a single DEFAULT_USER_AGENT in network_utils.py, project-generic
   by default (no contact info), overridable via SHADOWBROKER_USER_AGENT
   for operators who want to identify themselves (e.g. for Nominatim or
   weather.gov usage-policy compliance). Six call sites updated; the
   Nominatim-specific override is preserved.

4. The same generic UA now also flows through the peer prekey lookup
   in mesh_wormhole_prekey.py, so DM first-contact requests no longer
   identify the caller as a Shadowbroker fork to the peer being
   queried.

.env.example updated to document all new opt-in env vars.

Tests: backend/tests/test_control_surface_auth.py (extended),
       backend/tests/test_crowdthreat_opt_in.py (unchanged, still passes),
       backend/tests/test_third_party_fetchers_opt_in.py (new, 7 tests).
All 31 tests pass.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
BigBodyCobain
2026-05-18 13:53:33 -06:00
parent de27d119f9
commit 71a9d9e144
16 changed files with 289 additions and 18 deletions
@@ -52,6 +52,24 @@ import pytest
("post", "/api/wormhole/connect", {}),
("post", "/api/layers", {"layers": {"viirs_nightlights": True}}),
("post", "/api/ais/feed", {"msgs": []}),
# Added in post-#227 gap audit:
# /api/wormhole/join also calls bootstrap_wormhole_identity() — same
# identity-takeover surface as /identity/bootstrap. PR #227 hardened
# the latter but missed the former.
("post", "/api/wormhole/join", {}),
# /api/sigint/transmit relays APRS-IS packets over radio using
# operator-supplied credentials. Any caller who reaches this endpoint
# could transmit on the operator's authority. Must be local-only.
(
"post",
"/api/sigint/transmit",
{
"callsign": "N0CALL",
"passcode": "12345",
"target": "NOCALL",
"message": "test",
},
),
],
)
def test_remote_control_surface_rejects_without_local_operator_or_admin(
@@ -0,0 +1,106 @@
"""Third-party fetchers that phone home to politically/commercially
sensitive upstreams must be operator opt-in only.
Companion to ``test_crowdthreat_opt_in.py`` — extends the same default-off
posture to:
* EUvsDisinfo FIMI (``FIMI_ENABLED``)
* Polymarket + Kalshi (``PREDICTION_MARKETS_ENABLED``)
* Finnhub / yfinance financial data (``FINANCIAL_ENABLED`` /
``FINNHUB_API_KEY``)
* NUFORC HuggingFace dataset (``NUFORC_ENABLED``)
Each test asserts that with the env var unset (or set to a falsy value)
the fetcher's network entry point is NOT called.
"""
def _explode(*_args, **_kwargs):
raise AssertionError("upstream called while fetcher was meant to be disabled")
def test_fimi_disabled_by_default_does_not_call_upstream(monkeypatch):
from services.fetchers import _store, fimi
monkeypatch.delenv("FIMI_ENABLED", raising=False)
monkeypatch.setitem(_store.latest_data, "fimi", [{"id": "old"}])
monkeypatch.setattr(fimi, "fetch_with_curl", _explode)
fimi.fetch_fimi()
assert _store.latest_data["fimi"] == []
def test_fimi_falsy_value_does_not_call_upstream(monkeypatch):
from services.fetchers import _store, fimi
monkeypatch.setenv("FIMI_ENABLED", "false")
monkeypatch.setitem(_store.latest_data, "fimi", [{"id": "old"}])
monkeypatch.setattr(fimi, "fetch_with_curl", _explode)
fimi.fetch_fimi()
assert _store.latest_data["fimi"] == []
def test_prediction_markets_disabled_by_default(monkeypatch):
from services.fetchers import _store, prediction_markets
monkeypatch.delenv("PREDICTION_MARKETS_ENABLED", raising=False)
monkeypatch.setitem(_store.latest_data, "prediction_markets", [{"id": "old"}])
monkeypatch.setattr(
prediction_markets, "fetch_prediction_markets_raw", _explode
)
prediction_markets.fetch_prediction_markets()
assert _store.latest_data["prediction_markets"] == []
def test_financial_disabled_when_no_optin_or_api_key(monkeypatch):
"""yfinance fallback path must not run silently — needs FINANCIAL_ENABLED."""
from services.fetchers import _store, financial
monkeypatch.delenv("FINANCIAL_ENABLED", raising=False)
monkeypatch.delenv("FINNHUB_API_KEY", raising=False)
monkeypatch.setitem(_store.latest_data, "financial", {"BTC": {"price": 1}})
monkeypatch.setattr(financial, "_fetch_finnhub_quote", _explode)
monkeypatch.setattr(financial, "_fetch_yfinance_single", _explode)
financial.fetch_financial_markets()
assert _store.latest_data["financial"] == {}
def test_financial_enabled_via_finnhub_api_key(monkeypatch):
"""Presence of FINNHUB_API_KEY counts as explicit opt-in."""
from services.fetchers import financial
monkeypatch.delenv("FINANCIAL_ENABLED", raising=False)
monkeypatch.setenv("FINNHUB_API_KEY", "test-key")
assert financial.financial_fetch_enabled() is True
def test_nuforc_disabled_by_default_skips_download(monkeypatch):
from services.fetchers import nuforc_enrichment
monkeypatch.delenv("NUFORC_ENABLED", raising=False)
monkeypatch.setattr(nuforc_enrichment, "fetch_with_curl", _explode)
result = nuforc_enrichment._download_and_build()
assert result is None
def test_news_default_on_but_killable(monkeypatch):
"""News defaults on (kill switch only), but NEWS_ENABLED=false must disable it."""
from services.fetchers import _store, news
monkeypatch.setenv("NEWS_ENABLED", "false")
monkeypatch.setitem(_store.latest_data, "news", [{"id": "old"}])
monkeypatch.setattr(news, "fetch_with_curl", _explode)
news.fetch_news()
assert _store.latest_data["news"] == []