merge: testing → main (reconcile 2-week divergence)
This commit is contained in:
24
decnet/templates/mqtt/Dockerfile
Normal file
24
decnet/templates/mqtt/Dockerfile
Normal file
@@ -0,0 +1,24 @@
|
||||
ARG BASE_IMAGE=debian:bookworm-slim
|
||||
FROM ${BASE_IMAGE}
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
python3 \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
COPY syslog_bridge.py /opt/syslog_bridge.py
|
||||
COPY instance_seed.py /opt/instance_seed.py
|
||||
COPY server.py /opt/server.py
|
||||
COPY entrypoint.sh /entrypoint.sh
|
||||
RUN chmod +x /entrypoint.sh
|
||||
|
||||
EXPOSE 1883
|
||||
RUN useradd -r -s /bin/false -d /opt logrelay \
|
||||
&& apt-get update && apt-get install -y --no-install-recommends libcap2-bin \
|
||||
&& rm -rf /var/lib/apt/lists/* \
|
||||
&& (find /usr/bin/ -maxdepth 1 -name 'python3*' -type f -exec setcap 'cap_net_bind_service+eip' {} \; 2>/dev/null || true)
|
||||
|
||||
HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
|
||||
CMD kill -0 1 || exit 1
|
||||
|
||||
USER logrelay
|
||||
ENTRYPOINT ["/entrypoint.sh"]
|
||||
3
decnet/templates/mqtt/entrypoint.sh
Normal file
3
decnet/templates/mqtt/entrypoint.sh
Normal file
@@ -0,0 +1,3 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
exec python3 /opt/server.py
|
||||
120
decnet/templates/mqtt/instance_seed.py
Normal file
120
decnet/templates/mqtt/instance_seed.py
Normal file
@@ -0,0 +1,120 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Per-instance stealth seeding for honeypot service templates.
|
||||
|
||||
The whole decoy fleet looks identical to a scanner unless each decky
|
||||
diverges on the boring details: cluster UUIDs, auth salts, uptime, minor
|
||||
version strings, etc. This module derives a stable per-instance seed
|
||||
from NODE_NAME (+ optional INSTANCE_ID) and exposes helpers that return
|
||||
deterministic-per-decky-but-different-across-the-fleet values.
|
||||
|
||||
Connection-time jitter is intentionally NOT seeded — two hits to the same
|
||||
decky should not replay the same latency curve.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import os
|
||||
import random
|
||||
import time
|
||||
import uuid
|
||||
from typing import Sequence, TypeVar
|
||||
|
||||
T = TypeVar("T")
|
||||
|
||||
_HOSTNAME = (
|
||||
os.environ.get("NODE_NAME")
|
||||
or os.environ.get("HOSTNAME")
|
||||
or "decky"
|
||||
)
|
||||
_INSTANCE_ID = os.environ.get("INSTANCE_ID", "")
|
||||
_SEED_MATERIAL = f"{_HOSTNAME}:{_INSTANCE_ID}".encode()
|
||||
_SEED_INT = int.from_bytes(hashlib.sha256(_SEED_MATERIAL).digest()[:8], "big")
|
||||
|
||||
#: Deterministic RNG seeded per decky — use for *persistent* choices
|
||||
#: (versions, UUIDs, stored credentials). Never use for timing.
|
||||
rng = random.Random(_SEED_INT)
|
||||
|
||||
#: Process boot time — real uptime elapsed since container start.
|
||||
_PROCESS_START = time.time()
|
||||
|
||||
#: Deterministic per-instance fake "has been up for this long at boot"
|
||||
#: offset, so every decky pretends to have a different history.
|
||||
_BOOT_OFFSET = rng.randint(3600, 45 * 86400)
|
||||
|
||||
|
||||
def hostname() -> str:
|
||||
return _HOSTNAME
|
||||
|
||||
|
||||
def uptime_seconds() -> int:
|
||||
"""Monotonically increasing, unique per instance."""
|
||||
return int(_BOOT_OFFSET + (time.time() - _PROCESS_START))
|
||||
|
||||
|
||||
def boot_epoch() -> int:
|
||||
"""Fake wall-clock boot time for this instance (seconds since epoch)."""
|
||||
return int(time.time() - uptime_seconds())
|
||||
|
||||
|
||||
def instance_uuid(namespace: str = "") -> str:
|
||||
"""Deterministic UUID4-looking value for this instance+namespace."""
|
||||
ns = uuid.UUID("00000000-0000-0000-0000-000000000000")
|
||||
return str(uuid.uuid5(ns, f"{_HOSTNAME}:{namespace}"))
|
||||
|
||||
|
||||
def instance_hex(nbytes: int, namespace: str = "") -> str:
|
||||
"""Deterministic hex token of given byte length."""
|
||||
material = f"{_HOSTNAME}:{namespace}".encode()
|
||||
digest = hashlib.sha256(material).digest()
|
||||
while len(digest) < nbytes:
|
||||
digest += hashlib.sha256(digest).digest()
|
||||
return digest[:nbytes].hex()
|
||||
|
||||
|
||||
def pick(choices: Sequence[T]) -> T:
|
||||
"""Deterministic choice from a sequence."""
|
||||
return rng.choice(list(choices))
|
||||
|
||||
|
||||
def pick_weighted(choices: Sequence[tuple[T, float]]) -> T:
|
||||
"""Deterministic weighted choice. Input: [(item, weight), ...]."""
|
||||
total = sum(w for _, w in choices)
|
||||
r = rng.uniform(0, total)
|
||||
acc = 0.0
|
||||
for item, w in choices:
|
||||
acc += w
|
||||
if r <= acc:
|
||||
return item
|
||||
return choices[-1][0]
|
||||
|
||||
|
||||
def random_bytes(n: int, namespace: str = "") -> bytes:
|
||||
"""Deterministic per-instance byte string of length n."""
|
||||
out = bytearray()
|
||||
i = 0
|
||||
while len(out) < n:
|
||||
out.extend(
|
||||
hashlib.sha256(f"{_HOSTNAME}:{namespace}:{i}".encode()).digest()
|
||||
)
|
||||
i += 1
|
||||
return bytes(out[:n])
|
||||
|
||||
|
||||
def fresh_bytes(n: int) -> bytes:
|
||||
"""Non-deterministic random bytes — for per-connection nonces/salts."""
|
||||
return os.urandom(n)
|
||||
|
||||
|
||||
async def jitter(min_ms: int = 5, max_ms: int = 120) -> None:
|
||||
"""Async response-time jitter. Uses unseeded RNG so timing varies
|
||||
across connections to the same decky — seeded jitter would leak
|
||||
predictability."""
|
||||
await asyncio.sleep(random.uniform(min_ms, max_ms) / 1000.0)
|
||||
|
||||
|
||||
def jitter_sync(min_ms: int = 5, max_ms: int = 120) -> None:
|
||||
"""Blocking jitter for non-asyncio servers."""
|
||||
time.sleep(random.uniform(min_ms, max_ms) / 1000.0)
|
||||
340
decnet/templates/mqtt/server.py
Normal file
340
decnet/templates/mqtt/server.py
Normal file
@@ -0,0 +1,340 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
MQTT server (port 1883).
|
||||
Parses MQTT CONNECT packets, extracts client_id, etc.
|
||||
Responds with CONNACK.
|
||||
Supports dynamic topics and retained publishes.
|
||||
Logs PUBLISH commands sent by clients.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import struct
|
||||
|
||||
import instance_seed as _seed
|
||||
from syslog_bridge import (
|
||||
encode_secret,
|
||||
forward_syslog,
|
||||
syslog_line,
|
||||
write_syslog_file,
|
||||
)
|
||||
|
||||
NODE_NAME = os.environ.get("NODE_NAME", "mqtt-broker")
|
||||
SERVICE_NAME = "mqtt"
|
||||
LOG_TARGET = os.environ.get("LOG_TARGET", "")
|
||||
PORT = int(os.environ.get("PORT", "1883"))
|
||||
|
||||
# Default to auth-required. A broker that accepts literally anyone with any
|
||||
# client_id / username was realistic for devices on a flat OT LAN pre-2018,
|
||||
# but in 2024+ it's a tell. Operators who *want* the anonymous-broker decoy
|
||||
# still set MQTT_ACCEPT_ALL=1 explicitly.
|
||||
MQTT_ACCEPT_ALL = os.environ.get("MQTT_ACCEPT_ALL", "0") == "1"
|
||||
# Optional cred list (user:pass comma-separated). If set, only those combos
|
||||
# succeed even when ACCEPT_ALL is off — lets operators plant credential bait.
|
||||
_MQTT_CREDS: set[tuple[str, str]] = set()
|
||||
for combo in os.environ.get("MQTT_CREDS", "").split(","):
|
||||
combo = combo.strip()
|
||||
if ":" in combo:
|
||||
u, _, p = combo.partition(":")
|
||||
_MQTT_CREDS.add((u, p))
|
||||
|
||||
_PERSONA_CHOICES = ["water_plant", "building_hvac", "solar_farm", "factory_line"]
|
||||
MQTT_PERSONA = os.environ.get("MQTT_PERSONA") or _seed.pick(_PERSONA_CHOICES)
|
||||
MQTT_CUSTOM_TOPICS = os.environ.get("MQTT_CUSTOM_TOPICS", "")
|
||||
|
||||
# Fleet-diverse broker ID. Real mosquitto versions in the wild right now.
|
||||
_BROKER_VERSION = os.environ.get("MQTT_BROKER_VERSION") or _seed.pick([
|
||||
"mosquitto version 1.6.9",
|
||||
"mosquitto version 2.0.11",
|
||||
"mosquitto version 2.0.15",
|
||||
"mosquitto version 2.0.17",
|
||||
"mosquitto version 2.0.18",
|
||||
"HiveMQ CE 2024.4",
|
||||
"EMQX 5.3.2",
|
||||
])
|
||||
|
||||
_CONNACK_ACCEPTED = b"\x20\x02\x00\x00"
|
||||
_CONNACK_NOT_AUTH = b"\x20\x02\x00\x05"
|
||||
|
||||
|
||||
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)
|
||||
|
||||
|
||||
def _read_utf8(data: bytes, pos: int):
|
||||
"""Read MQTT UTF-8 string (2-byte length prefix). Returns (string, next_pos)."""
|
||||
if pos + 2 > len(data):
|
||||
return "", pos
|
||||
length = struct.unpack(">H", data[pos:pos + 2])[0]
|
||||
pos += 2
|
||||
return data[pos:pos + length].decode(errors="replace"), pos + length
|
||||
|
||||
|
||||
def _parse_connect(payload: bytes):
|
||||
pos = 0
|
||||
proto_name, pos = _read_utf8(payload, pos)
|
||||
if pos >= len(payload):
|
||||
return {}, pos
|
||||
_proto_level = payload[pos]
|
||||
pos += 1
|
||||
if pos >= len(payload):
|
||||
return {}, pos
|
||||
flags = payload[pos]
|
||||
pos += 1
|
||||
pos += 2 # Keep alive
|
||||
client_id, pos = _read_utf8(payload, pos)
|
||||
result = {"client_id": client_id, "proto": proto_name}
|
||||
if flags & 0x04:
|
||||
_, pos = _read_utf8(payload, pos)
|
||||
_, pos = _read_utf8(payload, pos)
|
||||
if flags & 0x80:
|
||||
username, pos = _read_utf8(payload, pos)
|
||||
result["username"] = username
|
||||
if flags & 0x40:
|
||||
password, pos = _read_utf8(payload, pos)
|
||||
result["password"] = password
|
||||
return result
|
||||
|
||||
|
||||
def _parse_subscribe(payload: bytes):
|
||||
"""Returns (packet_id, [(topic, qos), ...])"""
|
||||
if len(payload) < 2:
|
||||
return 0, []
|
||||
pos = 0
|
||||
packet_id = struct.unpack(">H", payload[pos:pos+2])[0]
|
||||
pos += 2
|
||||
topics = []
|
||||
while pos < len(payload):
|
||||
topic, pos = _read_utf8(payload, pos)
|
||||
if pos >= len(payload):
|
||||
break
|
||||
qos = payload[pos] & 0x03
|
||||
pos += 1
|
||||
topics.append((topic, qos))
|
||||
return packet_id, topics
|
||||
|
||||
|
||||
def _suback(packet_id: int, granted_qos: list[int]) -> bytes:
|
||||
payload = struct.pack(">H", packet_id) + bytes(granted_qos)
|
||||
return bytes([0x90, len(payload)]) + payload
|
||||
|
||||
|
||||
def _publish(topic: str, value: str, retain: bool = True) -> bytes:
|
||||
topic_bytes = topic.encode()
|
||||
topic_len = struct.pack(">H", len(topic_bytes))
|
||||
payload = str(value).encode()
|
||||
fixed = 0x31 if retain else 0x30
|
||||
remaining = len(topic_len) + len(topic_bytes) + len(payload)
|
||||
|
||||
# variable length encoding
|
||||
rem_bytes = []
|
||||
while remaining > 0:
|
||||
encoded = remaining % 128
|
||||
remaining = remaining // 128
|
||||
if remaining > 0:
|
||||
encoded = encoded | 128
|
||||
rem_bytes.append(encoded)
|
||||
if not rem_bytes:
|
||||
rem_bytes = [0]
|
||||
|
||||
return bytes([fixed]) + bytes(rem_bytes) + topic_len + topic_bytes + payload
|
||||
|
||||
|
||||
def _parse_publish(payload: bytes, qos: int):
|
||||
pos = 0
|
||||
topic, pos = _read_utf8(payload, pos)
|
||||
packet_id = 0
|
||||
if qos > 0:
|
||||
if pos + 2 <= len(payload):
|
||||
packet_id = struct.unpack(">H", payload[pos:pos+2])[0]
|
||||
pos += 2
|
||||
data = payload[pos:]
|
||||
return topic, packet_id, data
|
||||
|
||||
|
||||
def _generate_topics() -> dict:
|
||||
topics: dict = {}
|
||||
if MQTT_CUSTOM_TOPICS:
|
||||
try:
|
||||
topics = json.loads(MQTT_CUSTOM_TOPICS)
|
||||
return topics
|
||||
except Exception as e:
|
||||
_log("config_error", severity=4, error=str(e))
|
||||
|
||||
if MQTT_PERSONA == "water_plant":
|
||||
site = _seed.pick(["north", "south", "east", "west", "plant-a", "plant-b"])
|
||||
topics.update({
|
||||
f"{site}/water/tank1/level": f"{random.uniform(60.0, 80.0):.1f}",
|
||||
f"{site}/water/tank1/pressure": f"{random.uniform(2.5, 3.0):.2f}",
|
||||
f"{site}/water/pump1/status": "RUNNING",
|
||||
f"{site}/water/pump1/rpm": f"{int(random.uniform(1400, 1450))}",
|
||||
f"{site}/water/pump2/status": "STANDBY",
|
||||
f"{site}/water/chlorine/dosing": f"{random.uniform(1.1, 1.3):.1f}",
|
||||
f"{site}/water/chlorine/residual": f"{random.uniform(0.7, 0.9):.1f}",
|
||||
f"{site}/water/valve/inlet/state": "OPEN",
|
||||
f"{site}/water/valve/drain/state": "CLOSED",
|
||||
f"{site}/alarm/high_pressure": "0",
|
||||
f"{site}/alarm/low_chlorine": "0",
|
||||
f"{site}/alarm/pump_fault": "0",
|
||||
})
|
||||
elif MQTT_PERSONA == "building_hvac":
|
||||
floor = _seed.rng.randint(1, 12)
|
||||
for i in range(_seed.rng.randint(4, 10)):
|
||||
topics[f"bldg/floor{floor}/zone{i}/temp"] = f"{random.uniform(20.0, 24.5):.1f}"
|
||||
topics[f"bldg/floor{floor}/zone{i}/setpoint"] = f"{random.uniform(21.0, 23.0):.1f}"
|
||||
topics[f"bldg/floor{floor}/ahu/status"] = _seed.pick(["RUNNING", "RUNNING", "IDLE"])
|
||||
elif MQTT_PERSONA == "solar_farm":
|
||||
for arr in range(1, _seed.rng.randint(4, 9)):
|
||||
topics[f"solar/array{arr}/power_kw"] = f"{random.uniform(40.0, 180.0):.1f}"
|
||||
topics[f"solar/array{arr}/irradiance"] = f"{random.uniform(500, 950):.0f}"
|
||||
elif MQTT_PERSONA == "factory_line":
|
||||
line = _seed.pick(["A", "B", "C"])
|
||||
for m in range(1, _seed.rng.randint(3, 7)):
|
||||
topics[f"line{line}/machine{m}/state"] = _seed.pick(["RUN", "RUN", "IDLE", "FAULT"])
|
||||
topics[f"line{line}/machine{m}/cycle_count"] = str(_seed.rng.randint(1000, 999_999))
|
||||
if not topics:
|
||||
topics = {
|
||||
"device/status": "online",
|
||||
"device/uptime": str(_seed.uptime_seconds()),
|
||||
}
|
||||
# $SYS keys match every real broker.
|
||||
topics["$SYS/broker/version"] = _BROKER_VERSION
|
||||
topics["$SYS/broker/uptime"] = f"{_seed.uptime_seconds()} seconds"
|
||||
topics["$SYS/broker/clients/connected"] = str(_seed.rng.randint(2, 24))
|
||||
return topics
|
||||
|
||||
|
||||
class MQTTProtocol(asyncio.Protocol):
|
||||
def __init__(self):
|
||||
self._transport = None
|
||||
self._peer = None
|
||||
self._buf = b""
|
||||
self._auth = False
|
||||
self._topics = _generate_topics()
|
||||
|
||||
def connection_made(self, transport):
|
||||
self._transport = transport
|
||||
self._peer = transport.get_extra_info("peername", ("?", 0))
|
||||
_log("connect", src=self._peer[0], src_port=self._peer[1])
|
||||
|
||||
def data_received(self, data):
|
||||
self._buf += data
|
||||
try:
|
||||
self._process()
|
||||
except Exception as e:
|
||||
_log("protocol_error", severity=4, error=str(e))
|
||||
if self._transport:
|
||||
self._transport.close()
|
||||
|
||||
def _process(self):
|
||||
while len(self._buf) >= 2:
|
||||
pkt_byte = self._buf[0]
|
||||
pkt_type = (pkt_byte >> 4) & 0x0f
|
||||
flags = pkt_byte & 0x0f
|
||||
qos = (flags >> 1) & 0x03
|
||||
|
||||
# Decode remaining length (variable-length encoding)
|
||||
pos = 1
|
||||
remaining = 0
|
||||
multiplier = 1
|
||||
while pos < len(self._buf):
|
||||
if pos > 4: # MQTT spec: max 4 bytes for remaining length
|
||||
self._transport.close()
|
||||
self._buf = b""
|
||||
return
|
||||
byte = self._buf[pos]
|
||||
remaining += (byte & 0x7f) * multiplier
|
||||
multiplier *= 128
|
||||
pos += 1
|
||||
if not (byte & 0x80):
|
||||
break
|
||||
else:
|
||||
return # incomplete length
|
||||
if len(self._buf) < pos + remaining:
|
||||
return # incomplete payload
|
||||
payload = self._buf[pos:pos + remaining]
|
||||
self._buf = self._buf[pos + remaining:]
|
||||
|
||||
if pkt_type == 1: # CONNECT
|
||||
info = _parse_connect(payload)
|
||||
# Migrate auth event to the universal credential SD shape
|
||||
# so the ingester's native branch picks up the row. The
|
||||
# legacy username/password keys are intentionally NOT
|
||||
# forwarded — encode_secret() supplies secret_printable
|
||||
# and secret_b64 in their place.
|
||||
_user = info.get("username", "")
|
||||
_password = info.get("password", "")
|
||||
_passthrough = {k: v for k, v in info.items()
|
||||
if k not in ("username", "password")}
|
||||
_log("auth", username=_user, principal=_user,
|
||||
**encode_secret(_password), **_passthrough)
|
||||
# Decide connection: accept-all > cred list > deny.
|
||||
cred = (info.get("username", ""), info.get("password", ""))
|
||||
accepted = (
|
||||
MQTT_ACCEPT_ALL
|
||||
or (cred in _MQTT_CREDS if _MQTT_CREDS else False)
|
||||
)
|
||||
if accepted:
|
||||
self._auth = True
|
||||
self._transport.write(_CONNACK_ACCEPTED)
|
||||
else:
|
||||
self._transport.write(_CONNACK_NOT_AUTH)
|
||||
self._transport.close()
|
||||
elif pkt_type == 8: # SUBSCRIBE
|
||||
if not self._auth:
|
||||
self._transport.close()
|
||||
continue
|
||||
packet_id, subs = _parse_subscribe(payload)
|
||||
granted_qos = [1] * len(subs) # grant QoS 1 for all
|
||||
self._transport.write(_suback(packet_id, granted_qos))
|
||||
|
||||
# Immediately send retained publishes matching topics
|
||||
for sub_topic, _ in subs:
|
||||
_log("subscribe", src=self._peer[0], topics=[sub_topic])
|
||||
for t, v in self._topics.items():
|
||||
# simple match: if topic ends with #, it matches prefix
|
||||
if sub_topic.endswith("#"):
|
||||
prefix = sub_topic[:-1]
|
||||
if t.startswith(prefix):
|
||||
self._transport.write(_publish(t, str(v)))
|
||||
elif sub_topic == t:
|
||||
self._transport.write(_publish(t, str(v)))
|
||||
|
||||
elif pkt_type == 3: # PUBLISH
|
||||
if not self._auth:
|
||||
self._transport.close()
|
||||
continue
|
||||
topic, packet_id, data = _parse_publish(payload, qos)
|
||||
# Attacker command received!
|
||||
_log("publish", src=self._peer[0], topic=topic, payload=data.decode(errors="replace"))
|
||||
|
||||
if qos == 1:
|
||||
puback = bytes([0x40, 0x02]) + struct.pack(">H", packet_id)
|
||||
self._transport.write(puback)
|
||||
|
||||
elif pkt_type == 12: # PINGREQ
|
||||
self._transport.write(b"\xd0\x00") # PINGRESP
|
||||
elif pkt_type == 14: # DISCONNECT
|
||||
self._transport.close()
|
||||
else:
|
||||
_log("packet", src=self._peer[0], pkt_type=pkt_type)
|
||||
self._transport.close()
|
||||
|
||||
def connection_lost(self, exc):
|
||||
_log("disconnect", src=self._peer[0] if self._peer else "?")
|
||||
|
||||
|
||||
async def main():
|
||||
_log("startup", msg=f"MQTT server starting as {NODE_NAME}")
|
||||
loop = asyncio.get_running_loop()
|
||||
server = await loop.create_server(MQTTProtocol, "0.0.0.0", PORT) # nosec B104
|
||||
async with server:
|
||||
await server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
261
decnet/templates/mqtt/syslog_bridge.py
Normal file
261
decnet/templates/mqtt/syslog_bridge.py
Normal file
@@ -0,0 +1,261 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Shared RFC 5424 syslog helper used by service containers.
|
||||
|
||||
Services call syslog_line() to format an RFC 5424 message, then
|
||||
write_syslog_file() to emit it to stdout — the container runtime
|
||||
captures it, and the host-side collector streams it into the log file.
|
||||
|
||||
RFC 5424 structure:
|
||||
<PRI>1 TIMESTAMP HOSTNAME APP-NAME PROCID MSGID [SD-ELEMENT] MSG
|
||||
|
||||
Facility: local0 (16). SD element ID uses PEN 55555.
|
||||
"""
|
||||
|
||||
import base64
|
||||
import re
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any, Optional
|
||||
|
||||
# ─── Constants ────────────────────────────────────────────────────────────────
|
||||
|
||||
_FACILITY_LOCAL0 = 16
|
||||
_SD_ID = "relay@55555"
|
||||
_NILVALUE = "-"
|
||||
|
||||
SEVERITY_EMERG = 0
|
||||
SEVERITY_ALERT = 1
|
||||
SEVERITY_CRIT = 2
|
||||
SEVERITY_ERROR = 3
|
||||
SEVERITY_WARNING = 4
|
||||
SEVERITY_NOTICE = 5
|
||||
SEVERITY_INFO = 6
|
||||
SEVERITY_DEBUG = 7
|
||||
|
||||
_MAX_HOSTNAME = 255
|
||||
_MAX_APPNAME = 48
|
||||
_MAX_MSGID = 32
|
||||
|
||||
# ─── Formatter ────────────────────────────────────────────────────────────────
|
||||
|
||||
def _sd_escape(value: str) -> str:
|
||||
"""Escape SD-PARAM-VALUE per RFC 5424 §6.3.3."""
|
||||
return value.replace("\\", "\\\\").replace('"', '\\"').replace("]", "\\]")
|
||||
|
||||
|
||||
def _sd_element(fields: dict[str, Any]) -> str:
|
||||
if not fields:
|
||||
return _NILVALUE
|
||||
params = " ".join(f'{k}="{_sd_escape(str(v))}"' for k, v in fields.items())
|
||||
return f"[{_SD_ID} {params}]"
|
||||
|
||||
|
||||
def syslog_line(
|
||||
service: str,
|
||||
hostname: str,
|
||||
event_type: str,
|
||||
severity: int = SEVERITY_INFO,
|
||||
timestamp: datetime | None = None,
|
||||
msg: str | None = None,
|
||||
**fields: Any,
|
||||
) -> str:
|
||||
"""
|
||||
Return a single RFC 5424-compliant syslog line (no trailing newline).
|
||||
|
||||
Args:
|
||||
service: APP-NAME (e.g. "http", "mysql")
|
||||
hostname: HOSTNAME (node name)
|
||||
event_type: MSGID (e.g. "request", "login_attempt")
|
||||
severity: Syslog severity integer (default: INFO=6)
|
||||
timestamp: UTC datetime; defaults to now
|
||||
msg: Optional free-text MSG
|
||||
**fields: Encoded as structured data params
|
||||
"""
|
||||
pri = f"<{_FACILITY_LOCAL0 * 8 + severity}>"
|
||||
ts = (timestamp or datetime.now(timezone.utc)).isoformat()
|
||||
host = (hostname or _NILVALUE)[:_MAX_HOSTNAME]
|
||||
appname = (service or _NILVALUE)[:_MAX_APPNAME]
|
||||
msgid = (event_type or _NILVALUE)[:_MAX_MSGID]
|
||||
sd = _sd_element(fields)
|
||||
message = f" {msg}" if msg else ""
|
||||
return f"{pri}1 {ts} {host} {appname} {_NILVALUE} {msgid} {sd}{message}"
|
||||
|
||||
|
||||
def encode_secret(secret: str) -> dict[str, str]:
|
||||
"""Standardized credential-secret encoding for the universal SD-block shape.
|
||||
|
||||
Returns ``{'secret_printable': ..., 'secret_b64': ...}`` ready to spread
|
||||
into a :func:`syslog_line` / ``_log`` call::
|
||||
|
||||
_log("auth_attempt", principal=user, **encode_secret(password))
|
||||
|
||||
``secret_printable`` mirrors auth-helper.c's sd_escape: bytes outside
|
||||
``[0x20, 0x7f)`` collapse to ``'?'`` so the field is always parser-safe
|
||||
RFC 5424 ASCII. ``secret_b64`` preserves the *original* utf-8 bytes —
|
||||
NUL/0xff/control/non-utf8 sequences all survive losslessly, useful as
|
||||
a fingerprinting signal even when the printable form sanitizes them.
|
||||
|
||||
The decnet web ingester's native-shape branch keys off ``secret_b64``
|
||||
being present, so any service emitter calling this helper lands its
|
||||
cred attempt directly in the :class:`Credential` table.
|
||||
"""
|
||||
raw = secret.encode("utf-8", errors="replace")
|
||||
printable = "".join(chr(b) if 0x20 <= b < 0x7f else "?" for b in raw)
|
||||
return {
|
||||
"secret_printable": printable,
|
||||
"secret_b64": base64.b64encode(raw).decode("ascii"),
|
||||
}
|
||||
|
||||
|
||||
_DIGEST_PARAM_RE = re.compile(r'(\w+)\s*=\s*"([^"]*)"|(\w+)\s*=\s*([^,\s]+)')
|
||||
|
||||
|
||||
def classify_authorization(header_value: Optional[str]) -> Optional[dict[str, Any]]:
|
||||
"""Parse an HTTP Authorization header value into Credential SD fields.
|
||||
|
||||
Returns a dict with the universal cred shape ready to spread into a
|
||||
``_log(...)`` call::
|
||||
|
||||
auth = request.headers.get("Authorization")
|
||||
cred = classify_authorization(auth)
|
||||
if cred:
|
||||
_log("auth_attempt", **cred)
|
||||
|
||||
Recognised schemes:
|
||||
* Basic — base64(user:pw); decoded → ``principal=user`` +
|
||||
``secret_kind="plaintext"`` + ``encode_secret(pw)``.
|
||||
* Bearer / Token — opaque token; ``principal=None`` +
|
||||
``secret_kind="http_bearer"`` + ``encode_secret(token)``.
|
||||
* Digest — ``principal=username`` from header +
|
||||
``secret_kind="http_digest_md5"`` + ``encode_secret(response)``.
|
||||
|
||||
Returns ``None`` for anything unrecognized (AWS4-HMAC-SHA256, NTLM,
|
||||
Negotiate, …) — callers can still log the raw header value in the
|
||||
ambient SD-block; we just don't know how to extract a hashable
|
||||
secret from it.
|
||||
"""
|
||||
if not header_value or not isinstance(header_value, str):
|
||||
return None
|
||||
parts = header_value.strip().split(None, 1)
|
||||
if len(parts) < 2:
|
||||
return None
|
||||
scheme, rest = parts[0].lower(), parts[1].strip()
|
||||
|
||||
if scheme == "basic":
|
||||
try:
|
||||
decoded = base64.b64decode(rest, validate=True).decode("utf-8", errors="replace")
|
||||
except (ValueError, base64.binascii.Error):
|
||||
return None
|
||||
if ":" not in decoded:
|
||||
return None
|
||||
user, _, pw = decoded.partition(":")
|
||||
return {
|
||||
"principal": user,
|
||||
"secret_kind": "plaintext",
|
||||
**encode_secret(pw),
|
||||
}
|
||||
|
||||
if scheme in ("bearer", "token"):
|
||||
return {
|
||||
"principal": None,
|
||||
"secret_kind": "http_bearer",
|
||||
**encode_secret(rest),
|
||||
}
|
||||
|
||||
if scheme == "digest":
|
||||
params: dict[str, str] = {}
|
||||
for m in _DIGEST_PARAM_RE.finditer(rest):
|
||||
k = m.group(1) or m.group(3)
|
||||
v = m.group(2) if m.group(2) is not None else m.group(4)
|
||||
if k:
|
||||
params[k.lower()] = v
|
||||
response = params.get("response")
|
||||
if not response:
|
||||
return None
|
||||
return {
|
||||
"principal": params.get("username"),
|
||||
"secret_kind": "http_digest_md5",
|
||||
**encode_secret(response),
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
|
||||
_FORM_PRINCIPAL_KEYS = (
|
||||
"username", "user", "email", "login", "userid", "account",
|
||||
"log", # wp-login.php
|
||||
"user_login", # WordPress alt
|
||||
"uname", # phpMyAdmin
|
||||
"pma_username",
|
||||
)
|
||||
_FORM_SECRET_KEYS = (
|
||||
"password", "pass", "pwd", "passwd", "passwort", "mot_de_passe",
|
||||
"user_password", # WordPress alt
|
||||
"pma_password", # phpMyAdmin
|
||||
)
|
||||
|
||||
|
||||
def extract_form_credentials(
|
||||
body: Optional[str],
|
||||
content_type: Optional[str],
|
||||
) -> Optional[dict[str, Any]]:
|
||||
"""Parse an `application/x-www-form-urlencoded` body for credentials.
|
||||
|
||||
Returns the universal cred SD shape ready to spread into a
|
||||
``_log(...)`` call when both a principal-shaped key and a secret-
|
||||
shaped key are present in the body. Otherwise returns ``None``.
|
||||
|
||||
Field-name detection is case-insensitive and covers the most common
|
||||
login-form variants (WordPress wp-login.php, phpMyAdmin, Joomla,
|
||||
etc.). Add more entries to ``_FORM_PRINCIPAL_KEYS`` /
|
||||
``_FORM_SECRET_KEYS`` as new templates surface them.
|
||||
"""
|
||||
if not body or not isinstance(content_type, str):
|
||||
return None
|
||||
if not content_type.lower().startswith("application/x-www-form-urlencoded"):
|
||||
return None
|
||||
|
||||
fields: dict[str, str] = {}
|
||||
for pair in body.split("&"):
|
||||
if "=" not in pair:
|
||||
continue
|
||||
k, _, v = pair.partition("=")
|
||||
# urllib decode without importing urllib at module scope (the
|
||||
# template emitters are import-cost-sensitive). Inline the
|
||||
# tiny percent-decode + plus-decode.
|
||||
try:
|
||||
from urllib.parse import unquote_plus
|
||||
key = unquote_plus(k).lower()
|
||||
val = unquote_plus(v)
|
||||
except Exception:
|
||||
continue
|
||||
# First-wins so duplicate-key forms don't get clobbered.
|
||||
fields.setdefault(key, val)
|
||||
|
||||
principal: Optional[str] = None
|
||||
for k in _FORM_PRINCIPAL_KEYS:
|
||||
if k in fields:
|
||||
principal = fields[k]
|
||||
break
|
||||
secret: Optional[str] = None
|
||||
for k in _FORM_SECRET_KEYS:
|
||||
if k in fields:
|
||||
secret = fields[k]
|
||||
break
|
||||
if secret is None:
|
||||
return None
|
||||
return {
|
||||
"principal": principal,
|
||||
"secret_kind": "plaintext",
|
||||
**encode_secret(secret),
|
||||
}
|
||||
|
||||
|
||||
def write_syslog_file(line: str) -> None:
|
||||
"""Emit a syslog line to stdout for container log capture."""
|
||||
print(line, flush=True)
|
||||
|
||||
|
||||
def forward_syslog(line: str, log_target: str) -> None:
|
||||
"""No-op stub. TCP forwarding is handled by rsyslog, not by service containers."""
|
||||
pass
|
||||
Reference in New Issue
Block a user