Files
DECNET/decnet/templates/http/server.py
anti 3404e3b3a6 feat(creds): Phase 1 — Authorization header + SNMP community capture
Closes the cred-coverage gap for 7 services that already had the data
on the wire but never landed it in the Credential table:

- SNMP — community string lands as secret_kind="snmp_community",
  principal=None (v1/v2c has no per-user identity, the community IS
  the auth).
- SIP — Digest response hash, previously buried in the auth= header
  dump, now classify_authorization()-extracted.
- HTTP / HTTPS — Authorization header was in the headers JSON but
  never extracted. Now Basic decodes to plaintext, Bearer →
  http_bearer (principal=None), Digest → http_digest_md5.
- K8s — already extracted Authorization but didn't normalize. Service-
  account JWTs flow through as Bearer.
- Docker API — headers absent entirely. Adds the headers JSON dump
  and runs Authorization through the classifier.
- Elasticsearch — five distinct request handlers; each gains a
  per-handler _cred_fields() helper.

Adds canonical templates/syslog_bridge.py:classify_authorization().
Recognised: Basic / Bearer / Token / Digest. Unknown schemes (NTLM,
AWS4-HMAC, Negotiate) return None; the header still rides in the
ambient SD-block but isn't normalized as a credential. The SD shape
on the wire collapses sip_digest_md5 into http_digest_md5 — same
algorithm, so cross-protocol reuse correlates correctly when (rare)
nonce collisions allow.

Drive-by repair of tests/core/test_fingerprinting.py:

- The pre-existing `test_http_useragent_extracted` asserted both that
  add_bounty was called exactly once AND that the UA payload carried
  `path` and `method` fields. Both wrong since this session opened:
  the http_quirks fingerprint added later fires too, and the UA
  payload never actually included path/method despite the assertion.
- Adds `path`/`method` to the UA fingerprint payload (real operator
  value: "Nikto hit /admin" beats "Nikto seen on this decky").
- Replaces `assert_awaited_once` with a `_find_ua_bounty()` helper
  that filters add_bounty calls by `fingerprint_type`. New fingerprint
  families landing later won't retroactively break old tests.
- Updates the two credential-bearing tests to use the post-DEBT-039
  native shape (`secret_b64` / `principal`) and `upsert_credential`,
  not the deleted legacy `username+password` adapter.

Also rebuilds the per-service fake `syslog_bridge` modules in
tests/service_testing/{conftest,test_imap,test_pop3,test_snmp,test_mqtt,test_smtp}.py
to expose `encode_secret` + `classify_authorization`. Service templates
that import either now no longer fail at test collection.

173 tests pass in the touched scope. Phases 2-7 still pending.
2026-04-25 07:04:10 -04:00

158 lines
5.5 KiB
Python

#!/usr/bin/env python3
"""
HTTP service emulator using Flask.
Accepts all requests, logs every detail (method, path, headers, body),
and responds with configurable pages. Forwards events as JSON to LOG_TARGET if set.
"""
import json
import logging
import os
from pathlib import Path
from flask import Flask, request, send_from_directory
from werkzeug.serving import make_server, WSGIRequestHandler
import instance_seed as _seed
from syslog_bridge import (
classify_authorization,
forward_syslog,
syslog_line,
write_syslog_file,
)
logging.getLogger("werkzeug").setLevel(logging.ERROR)
NODE_NAME = os.environ.get("NODE_NAME", "webserver")
SERVICE_NAME = "http"
LOG_TARGET = os.environ.get("LOG_TARGET", "")
PORT = int(os.environ.get("PORT", "80"))
# Per-instance Server header. Every decky running one identical Apache
# version string is a one-query fleet discovery for any scanner.
# Distribution shaped toward currently-deployed-in-the-wild versions.
_SERVER_CHOICES = [
"Apache/2.4.41 (Ubuntu)",
"Apache/2.4.52 (Ubuntu)",
"Apache/2.4.54 (Debian)",
"Apache/2.4.56 (Debian)",
"Apache/2.4.57 (Debian)",
"Apache/2.4.58 (Ubuntu)",
"Apache/2.4.59 (Debian)",
"nginx/1.18.0 (Ubuntu)",
"nginx/1.22.1",
"nginx/1.24.0 (Ubuntu)",
"nginx/1.25.3",
]
SERVER_HEADER = os.environ.get("SERVER_HEADER") or _seed.pick(_SERVER_CHOICES)
RESPONSE_CODE = int(os.environ.get("RESPONSE_CODE", "403"))
FAKE_APP = os.environ.get("FAKE_APP", "")
EXTRA_HEADERS = json.loads(os.environ.get("EXTRA_HEADERS", "{}"))
CUSTOM_BODY = os.environ.get("CUSTOM_BODY", "")
FILES_DIR = os.environ.get("FILES_DIR", "")
_FAKE_APP_BODIES: dict[str, str] = {
"apache_default": (
"<!DOCTYPE HTML PUBLIC \"-//IETF//DTD HTML 2.0//EN\">\n"
"<html><head><title>Apache2 Debian Default Page</title></head>\n"
"<body><h1>Apache2 Debian Default Page</h1>\n"
"<p>It works!</p></body></html>"
),
"nginx_default": (
"<!DOCTYPE html><html><head><title>Welcome to nginx!</title></head>\n"
"<body><h1>Welcome to nginx!</h1>\n"
"<p>If you see this page, the nginx web server is successfully installed.</p>\n"
"</body></html>"
),
"wordpress": (
"<!DOCTYPE html><html><head><title>WordPress &rsaquo; Error</title></head>\n"
"<body id=\"error-page\"><div class=\"wp-die-message\">\n"
"<h1>Error establishing a database connection</h1></div></body></html>"
),
"phpmyadmin": (
"<!DOCTYPE html><html><head><title>phpMyAdmin</title></head>\n"
"<body><form method=\"post\" action=\"index.php\">\n"
"<input type=\"text\" name=\"pma_username\" />\n"
"<input type=\"password\" name=\"pma_password\" />\n"
"<input type=\"submit\" value=\"Go\" /></form></body></html>"
),
"iis_default": (
"<!DOCTYPE html><html><head><title>IIS Windows Server</title></head>\n"
"<body><h1>IIS Windows Server</h1>\n"
"<p>Welcome to Internet Information Services</p></body></html>"
),
}
app = Flask(__name__)
@app.after_request
def _fix_server_header(response):
response.headers["Server"] = SERVER_HEADER
return response
def _log(event_type: str, severity: int = 6, **kwargs) -> None:
line = syslog_line(SERVICE_NAME, NODE_NAME, event_type, severity, **kwargs)
write_syslog_file(line)
forward_syslog(line, LOG_TARGET)
@app.before_request
def log_request():
# Classify Authorization → universal credential SD shape. Lands in
# the Credential table on Basic / Bearer / Digest; opaque schemes
# (NTLM, AWS4-HMAC-…) fall through and ride only in the headers
# dump. None when no Authorization header present.
cred = classify_authorization(request.headers.get("Authorization"))
_log(
"request",
method=request.method,
path=request.path,
remote_addr=request.remote_addr,
headers=json.dumps(dict(request.headers)),
body=request.get_data(as_text=True)[:512],
**(cred or {}),
)
@app.route("/", defaults={"path": ""})
@app.route("/<path:path>", methods=["GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS", "HEAD"])
def catch_all(path):
# Serve static files directory if configured
if FILES_DIR and path:
files_path = Path(FILES_DIR) / path
if files_path.is_file():
return send_from_directory(FILES_DIR, path)
# Select response body: custom > fake_app preset > default 403
if CUSTOM_BODY:
body = CUSTOM_BODY
elif FAKE_APP and FAKE_APP in _FAKE_APP_BODIES:
body = _FAKE_APP_BODIES[FAKE_APP]
else:
body = (
"<!DOCTYPE HTML PUBLIC \"-//IETF//DTD HTML 2.0//EN\">\n"
"<html><head>\n"
"<title>403 Forbidden</title>\n"
"</head><body>\n"
"<h1>Forbidden</h1>\n"
"<p>You don't have permission to access this resource.</p>\n"
"<hr>\n"
f"<address>{SERVER_HEADER} Server at {NODE_NAME} Port 80</address>\n"
"</body></html>\n"
)
headers = {"Content-Type": "text/html", **EXTRA_HEADERS}
return body, RESPONSE_CODE, headers
class _SilentHandler(WSGIRequestHandler):
"""Suppress Werkzeug's Server header so Flask's after_request is the sole source."""
def version_string(self) -> str:
return ""
if __name__ == "__main__":
_log("startup", msg=f"HTTP server starting as {NODE_NAME}")
srv = make_server("0.0.0.0", PORT, app, request_handler=_SilentHandler) # nosec B104
srv.serve_forever()