mirror of
https://github.com/BigBodyCobain/Shadowbroker.git
synced 2026-05-28 18:11:31 +02:00
Shadowbroker
76750caa92
== Per-install operator handle for every third-party API call ==
Before this PR, every Shadowbroker install identified itself to
Wikipedia, Wikidata, Nominatim, GDELT, OpenMHz, Broadcastify,
weather.gov, NUFORC, Sentinel/Planetary Computer, TinyGS / CelesTrak,
Shodan, Finnhub, and others with a single project-wide User-Agent
("Shadowbroker/1.0" or "ShadowBroker-OSINT/1.0"). From the upstream's
perspective every install in the world looked like one giant scraper.
If one install misbehaved, the upstream's only recourse was to block
"Shadowbroker" as a whole.
PR #284 inadvertently doubled down on this in the frontend by
introducing a shared `WIKIMEDIA_API_USER_AGENT` constant. This PR
retrofits both backends to per-operator attribution.
New setting: OPERATOR_HANDLE (env var / settings UI / auto-gen)
New helper: network_utils.outbound_user_agent("purpose")
The handle is auto-generated as "operator-XXXXXX" on first call (the
"shadow-" prefix from earlier drafts was deliberately dropped — too
suspicious-looking for abuse-detection systems). Operators can
override via OPERATOR_HANDLE; the value is sanitized to lowercase
alphanumeric+dash+underscore and capped at 48 chars. Persisted to
backend/data/operator_handle.json so it survives container restarts.
Retrofitted call sites (every previously-MONSTER User-Agent):
- services/region_dossier.py (Wikipedia + Wikidata + Nominatim)
- services/geocode.py (Nominatim)
- services/sentinel_search.py (Microsoft Planetary Computer)
- services/feed_ingester.py (operator-curated RSS feeds)
- services/fetchers/earth_observation.py (weather.gov, NUFORC)
- services/fetchers/infrastructure.py
- services/fetchers/aircraft_database.py
- services/fetchers/route_database.py
- services/fetchers/trains.py
- services/fetchers/meshtastic_map.py
- services/shodan_connector.py
- services/unusual_whales_connector.py (Finnhub)
- services/tinygs_fetcher.py (CelesTrak + TinyGS)
- services/sar/sar_products_client.py
- services/geopolitics.py (GDELT)
- services/radio_intercept.py (Broadcastify + OpenMHz)
- routers/cctv.py + main.py (CCTV proxy)
- routers/ai_intel.py
- scripts/convert_power_plants.py (release-time data refresh)
Spoofed browser UAs removed (issues #289 / #290 / #291 — tg12 audit):
- cloudscraper-based Chrome impersonation against api.openmhz.com
-> replaced with honest requests + per-install UA
- Mozilla/5.0 spoofed UA on Broadcastify scrape
-> replaced with honest UA
- Mozilla/5.0 + fake first-party Referer on OpenMHz audio relay
-> replaced with honest UA
- cloudscraper dependency dropped from pyproject.toml + uv.lock
Frontend retrofit:
- new GET /api/settings/operator-handle endpoint (local-operator
gated) returns the install's handle
- frontend/src/lib/wikimediaClient.ts fetches the handle once on
first use, caches it for page lifetime, embeds it in the
Api-User-Agent for every Wikipedia / Wikidata browser-direct call
== GDELT GCS-direct fix ==
GDELT's data.gdeltproject.org is a CNAME to a Google Cloud Storage
bucket. GCS responds with the wildcard *.storage.googleapis.com cert
which legitimately does NOT cover the GDELT custom domain, so Python's
TLS verification correctly refuses the connection. Some networks
happen to route through a path where this works; many (notably Docker
Desktop's outbound NAT on local installs) do not. Verified on the
maintainer's local install: GDELT was unreachable; 1610 geopolitical
events / 48 export files were dropping silently.
Fix: services/geopolitics._gcs_direct_gdelt_url() rewrites any
data.gdeltproject.org URL to its GCS-direct equivalent
(storage.googleapis.com/data.gdeltproject.org/...) where the standard
GCS cert is genuinely valid. api.gdeltproject.org and every other host
are left untouched.
Confirmed live: backend log goes from
GDELT lastupdate failed: 500
to
Downloading 48 GDELT export files...
Downloaded 48/48 GDELT exports
GDELT parsed: 1610 conflict locations from 48 files
== Tests ==
backend/tests/test_per_operator_outbound_attribution.py (12 tests)
backend/tests/test_gdelt_gcs_direct_rewrite.py (6 tests)
backend/tests/test_region_dossier_wikimedia_ua.py (updated to
pin the helper + per-operator handle, not the old constant)
frontend/src/__tests__/utils/wikimediaClient.test.ts (rewritten
to mock /api/settings/operator-handle and assert per-operator UA)
Local: backend 114/114 security+audit+round7a suite green;
frontend 718/718 vitest suite green.
Credit: tg12 (external security audit, issues #289/#290/#291
relating to spoofed UAs); BigBodyCobain (operator-prefix call,
GDELT cloud-vs-local diagnosis).
53 lines
1.4 KiB
TOML
53 lines
1.4 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=68.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.setuptools]
|
|
py-modules = []
|
|
|
|
[project]
|
|
name = "backend"
|
|
version = "0.9.79"
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"apscheduler==3.10.3",
|
|
"beautifulsoup4>=4.9.0",
|
|
"cachetools==5.5.2",
|
|
"cryptography>=41.0.0",
|
|
"defusedxml>=0.7.1",
|
|
"fastapi==0.115.12",
|
|
"feedparser==6.0.10",
|
|
"httpx==0.28.1",
|
|
"playwright==1.59.0",
|
|
"playwright-stealth==1.0.6",
|
|
"pydantic==2.13.3",
|
|
"pydantic-settings==2.8.1",
|
|
"pystac-client==0.8.6",
|
|
"python-dotenv==1.2.2",
|
|
"requests==2.31.0",
|
|
"PySocks==1.7.1",
|
|
"reverse-geocoder==1.5.1",
|
|
"sgp4==2.25",
|
|
"meshtastic>=2.5.0",
|
|
"orjson>=3.10.0",
|
|
"paho-mqtt>=1.6.0,<2.0.0",
|
|
"PyNaCl>=1.5.0",
|
|
"slowapi==0.1.9",
|
|
"vaderSentiment>=3.3.0",
|
|
"uvicorn==0.34.0",
|
|
"yfinance==1.3.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = ["pytest>=8.3.4", "pytest-asyncio==0.25.0", "ruff>=0.9.0", "black>=24.0.0"]
|
|
|
|
[tool.ruff.lint]
|
|
# The current backend carries historical style debt in large legacy modules.
|
|
# Keep CI focused on actionable correctness checks for the v0.9.79 release.
|
|
ignore = ["E401", "E402", "E701", "E731", "E741", "F401", "F402", "F541", "F811", "F841"]
|
|
|
|
[tool.black]
|
|
# Avoid a release-time whole-backend formatting rewrite. Re-enable by narrowing
|
|
# this once the legacy tree is formatted in a dedicated cleanup PR.
|
|
force-exclude = ".*"
|