merge: testing → main (reconcile 2-week divergence)
This commit is contained in:
24
decnet/templates/mongodb/Dockerfile
Normal file
24
decnet/templates/mongodb/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 27017
|
||||
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/mongodb/entrypoint.sh
Normal file
3
decnet/templates/mongodb/entrypoint.sh
Normal file
@@ -0,0 +1,3 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
exec python3 /opt/server.py
|
||||
120
decnet/templates/mongodb/instance_seed.py
Normal file
120
decnet/templates/mongodb/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)
|
||||
352
decnet/templates/mongodb/server.py
Normal file
352
decnet/templates/mongodb/server.py
Normal file
@@ -0,0 +1,352 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
MongoDBserver.
|
||||
Implements the MongoDB wire protocol OP_MSG/OP_QUERY handshake. Responds
|
||||
to isMaster/hello, listDatabases, and authenticate commands. Logs all
|
||||
received messages as JSON.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import base64
|
||||
import os
|
||||
import struct
|
||||
|
||||
import instance_seed as _seed
|
||||
from syslog_bridge import syslog_line, write_syslog_file, forward_syslog
|
||||
|
||||
|
||||
# ─── Minimal BSON walker ──────────────────────────────────────────────────────
|
||||
# Just enough to extract `saslStart` / `saslContinue` command auth fields.
|
||||
# Pulls a few BSON type codes; ignores everything else (subdocs returned
|
||||
# as raw bytes the caller can re-parse if needed). Hand-rolled rather
|
||||
# than pulling pymongo as a runtime dep — we only need 8 type codes and
|
||||
# the parser is ~40 LoC.
|
||||
|
||||
_BSON_DOUBLE = 0x01
|
||||
_BSON_STRING = 0x02
|
||||
_BSON_DOC = 0x03
|
||||
_BSON_ARRAY = 0x04
|
||||
_BSON_BINARY = 0x05
|
||||
_BSON_BOOL = 0x08
|
||||
_BSON_INT32 = 0x10
|
||||
_BSON_INT64 = 0x12
|
||||
|
||||
|
||||
def _bson_read(buf: bytes, off: int = 0) -> dict:
|
||||
"""Read a single BSON document at ``buf[off]``. Returns a dict of
|
||||
``{key: value}``. Lossy on unsupported types (silently skipped).
|
||||
Untrusted-input safe: bounds-checked, won't infinite-loop on
|
||||
malformed length fields."""
|
||||
out: dict = {}
|
||||
if off + 4 > len(buf):
|
||||
return out
|
||||
doc_len = struct.unpack_from("<i", buf, off)[0]
|
||||
end = off + doc_len
|
||||
if end > len(buf) or doc_len < 5:
|
||||
return out
|
||||
p = off + 4
|
||||
while p < end - 1: # last byte is the trailing 0x00
|
||||
t = buf[p]
|
||||
p += 1
|
||||
if t == 0:
|
||||
break
|
||||
# Read NUL-terminated cstring key.
|
||||
nul = buf.find(b"\x00", p, end)
|
||||
if nul < 0:
|
||||
break
|
||||
key = buf[p:nul].decode("utf-8", errors="replace")
|
||||
p = nul + 1
|
||||
if t == _BSON_STRING:
|
||||
if p + 4 > end:
|
||||
break
|
||||
slen = struct.unpack_from("<i", buf, p)[0]
|
||||
p += 4
|
||||
if p + slen > end or slen < 1:
|
||||
break
|
||||
out[key] = buf[p:p + slen - 1].decode("utf-8", errors="replace")
|
||||
p += slen
|
||||
elif t == _BSON_BINARY:
|
||||
if p + 5 > end:
|
||||
break
|
||||
blen = struct.unpack_from("<i", buf, p)[0]
|
||||
p += 4
|
||||
_subtype = buf[p]
|
||||
p += 1
|
||||
if p + blen > end or blen < 0:
|
||||
break
|
||||
out[key] = buf[p:p + blen] # raw bytes
|
||||
p += blen
|
||||
elif t == _BSON_INT32:
|
||||
if p + 4 > end:
|
||||
break
|
||||
out[key] = struct.unpack_from("<i", buf, p)[0]
|
||||
p += 4
|
||||
elif t == _BSON_INT64:
|
||||
if p + 8 > end:
|
||||
break
|
||||
out[key] = struct.unpack_from("<q", buf, p)[0]
|
||||
p += 8
|
||||
elif t == _BSON_BOOL:
|
||||
if p + 1 > end:
|
||||
break
|
||||
out[key] = buf[p] != 0
|
||||
p += 1
|
||||
elif t == _BSON_DOUBLE:
|
||||
p += 8
|
||||
elif t in (_BSON_DOC, _BSON_ARRAY):
|
||||
if p + 4 > end:
|
||||
break
|
||||
sub_len = struct.unpack_from("<i", buf, p)[0]
|
||||
if p + sub_len > end:
|
||||
break
|
||||
p += sub_len
|
||||
else:
|
||||
# Unsupported type — abort cleanly so we don't misalign.
|
||||
break
|
||||
return out
|
||||
|
||||
|
||||
def _scram_kv(payload: bytes) -> dict:
|
||||
"""Parse a SCRAM message into key=value pairs. SCRAM separates by
|
||||
commas and uses `name=value` pairs. We strip a leading `n,,` (GS2
|
||||
header) when present so the `n=username` shows up directly."""
|
||||
s = payload.decode("utf-8", errors="replace")
|
||||
if s.startswith("n,,"):
|
||||
s = s[3:]
|
||||
elif s.startswith("y,,"):
|
||||
s = s[3:]
|
||||
out: dict = {}
|
||||
for part in s.split(","):
|
||||
if "=" in part:
|
||||
k, _, v = part.partition("=")
|
||||
out[k.strip()] = v
|
||||
return out
|
||||
|
||||
NODE_NAME = os.environ.get("NODE_NAME", "mongodb")
|
||||
SERVICE_NAME = "mongodb"
|
||||
LOG_TARGET = os.environ.get("LOG_TARGET", "")
|
||||
PORT = int(os.environ.get("PORT", "27017"))
|
||||
|
||||
# Per-instance (version, maxWireVersion) — paired per real MongoDB release.
|
||||
# Wire version is locked to major/minor per upstream release notes.
|
||||
_MONGO_RELEASES = [
|
||||
("4.4.22", 9),
|
||||
("5.0.25", 13),
|
||||
("6.0.5", 17),
|
||||
("6.0.14", 17),
|
||||
("7.0.5", 21),
|
||||
("7.0.8", 21),
|
||||
("7.0.11", 21),
|
||||
]
|
||||
_MONGO_VERSION, _MONGO_WIRE = _seed.pick(_MONGO_RELEASES)
|
||||
_MONGO_SET_NAME = os.environ.get("MONGO_REPL_SET", "") # empty = standalone
|
||||
|
||||
|
||||
def _new_objectid() -> bytes:
|
||||
"""12-byte BSON ObjectId — fresh per call."""
|
||||
return _seed.fresh_bytes(12)
|
||||
|
||||
# Minimal BSON helpers
|
||||
def _bson_str(key: str, val: str) -> bytes:
|
||||
k = key.encode() + b"\x00"
|
||||
v = val.encode() + b"\x00"
|
||||
return b"\x02" + k + struct.pack("<I", len(v)) + v
|
||||
|
||||
def _bson_int32(key: str, val: int) -> bytes:
|
||||
return b"\x10" + key.encode() + b"\x00" + struct.pack("<i", val)
|
||||
|
||||
def _bson_bool(key: str, val: bool) -> bytes:
|
||||
return b"\x08" + key.encode() + b"\x00" + (b"\x01" if val else b"\x00")
|
||||
|
||||
def _bson_doc(*fields: bytes) -> bytes:
|
||||
body = b"".join(fields) + b"\x00"
|
||||
return struct.pack("<I", len(body) + 4) + body
|
||||
|
||||
def _op_reply(request_id: int, doc: bytes) -> bytes:
|
||||
# OP_REPLY header: total_len(4), req_id(4), response_to(4), opcode(4)=1,
|
||||
# flags(4), cursor_id(8), starting_from(4), number_returned(4), docs
|
||||
header = struct.pack(
|
||||
"<iiiiiqii",
|
||||
16 + 20 + len(doc), # total length
|
||||
0, # request id
|
||||
request_id, # response to
|
||||
1, # OP_REPLY
|
||||
0, # flags
|
||||
0, # cursor id (int64)
|
||||
0, # starting from
|
||||
1, # number returned
|
||||
)
|
||||
return header + doc
|
||||
|
||||
def _op_msg(request_id: int, doc: bytes) -> bytes:
|
||||
payload = b"\x00" + doc
|
||||
flag_bits = struct.pack("<I", 0)
|
||||
msg_body = flag_bits + payload
|
||||
header = struct.pack("<iiii",
|
||||
16 + len(msg_body),
|
||||
1,
|
||||
request_id,
|
||||
2013,
|
||||
)
|
||||
return header + msg_body
|
||||
|
||||
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)
|
||||
|
||||
|
||||
class MongoDBProtocol(asyncio.Protocol):
|
||||
def __init__(self):
|
||||
self._transport = None
|
||||
self._peer = None
|
||||
self._buf = b""
|
||||
# Per-connection SCRAM state: pinned at saslStart so the
|
||||
# subsequent saslContinue's client-proof can carry the username
|
||||
# in the emitted credential row.
|
||||
self._sasl_username: str | None = None
|
||||
self._sasl_mechanism: str | None = None
|
||||
|
||||
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
|
||||
while len(self._buf) >= 16:
|
||||
msg_len = struct.unpack("<I", self._buf[:4])[0]
|
||||
if msg_len < 16 or msg_len > 48 * 1024 * 1024:
|
||||
self._transport.close()
|
||||
self._buf = b""
|
||||
return
|
||||
if len(self._buf) < msg_len:
|
||||
break
|
||||
msg = self._buf[:msg_len]
|
||||
self._buf = self._buf[msg_len:]
|
||||
self._handle_message(msg)
|
||||
|
||||
def _handle_message(self, msg: bytes):
|
||||
if len(msg) < 16:
|
||||
return
|
||||
request_id = struct.unpack("<I", msg[4:8])[0]
|
||||
opcode = struct.unpack("<I", msg[12:16])[0]
|
||||
_log("message", src=self._peer[0], opcode=opcode, length=len(msg))
|
||||
|
||||
# SCRAM cred capture: parse the OP_MSG body BSON looking for
|
||||
# saslStart / saslContinue. Each fires its own log event:
|
||||
# saslStart pins the username + mechanism; saslContinue emits
|
||||
# the credential row with the client-proof as secret_b64.
|
||||
if opcode == 2013 and len(msg) >= 21:
|
||||
# OP_MSG body: 4 bytes flagBits, then sections. We only
|
||||
# parse kind=0 (Body) sections — kind=1 (DocSeq) is for
|
||||
# bulk ops that don't carry SCRAM auth.
|
||||
p = 20 # 16 hdr + 4 flagBits
|
||||
while p < len(msg):
|
||||
kind = msg[p]
|
||||
p += 1
|
||||
if kind == 0: # Body section
|
||||
if p + 4 > len(msg):
|
||||
break
|
||||
doc_len = struct.unpack_from("<i", msg, p)[0]
|
||||
if p + doc_len > len(msg):
|
||||
break
|
||||
cmd = _bson_read(msg, p)
|
||||
self._handle_command(cmd)
|
||||
p += doc_len
|
||||
elif kind == 1: # DocSeq — skip
|
||||
if p + 4 > len(msg):
|
||||
break
|
||||
seq_len = struct.unpack_from("<i", msg, p)[0]
|
||||
p += seq_len
|
||||
else:
|
||||
break
|
||||
|
||||
# Build a generic isMaster-style OK response with this instance's
|
||||
# version pair. Fresh topologyVersion on every reply (matches real
|
||||
# mongod behavior — clients use this to detect failover).
|
||||
fields = [
|
||||
_bson_bool("ismaster", True),
|
||||
_bson_bool("helloOk", True),
|
||||
_bson_int32("maxBsonObjectSize", 16777216),
|
||||
_bson_int32("maxMessageSizeBytes", 48000000),
|
||||
_bson_int32("maxWriteBatchSize", 100000),
|
||||
_bson_int32("maxWireVersion", _MONGO_WIRE),
|
||||
_bson_int32("minWireVersion", 0),
|
||||
_bson_str("version", _MONGO_VERSION),
|
||||
_bson_int32("ok", 1),
|
||||
]
|
||||
if _MONGO_SET_NAME:
|
||||
fields.insert(1, _bson_str("setName", _MONGO_SET_NAME))
|
||||
reply_doc = _bson_doc(*fields)
|
||||
if opcode == 2013: # OP_MSG
|
||||
self._transport.write(_op_msg(request_id, reply_doc))
|
||||
else:
|
||||
self._transport.write(_op_reply(request_id, reply_doc))
|
||||
|
||||
def _handle_command(self, cmd: dict) -> None:
|
||||
"""Parse a single MongoDB command document for SCRAM auth.
|
||||
|
||||
saslStart — client-first-message in payload. Extract
|
||||
`n=<username>` so the next saslContinue inherits it.
|
||||
saslContinue — client-final-message in payload. Extract
|
||||
`p=<base64 client-proof>` and emit a cred row.
|
||||
"""
|
||||
# mongo's command dispatch keys off the FIRST field of the BSON
|
||||
# document. We just check key presence since dict ordering in
|
||||
# CPython 3.7+ matches insertion order.
|
||||
if "saslStart" in cmd:
|
||||
mechanism = cmd.get("mechanism")
|
||||
payload = cmd.get("payload") or b""
|
||||
if isinstance(mechanism, str):
|
||||
self._sasl_mechanism = mechanism
|
||||
if isinstance(payload, (bytes, bytearray)):
|
||||
kv = _scram_kv(bytes(payload))
|
||||
self._sasl_username = kv.get("n")
|
||||
_log("auth_start", src=self._peer[0],
|
||||
mechanism=mechanism or "?",
|
||||
username=self._sasl_username or "")
|
||||
return
|
||||
|
||||
if "saslContinue" in cmd:
|
||||
payload = cmd.get("payload") or b""
|
||||
if not isinstance(payload, (bytes, bytearray)):
|
||||
return
|
||||
kv = _scram_kv(bytes(payload))
|
||||
proof_b64 = kv.get("p")
|
||||
if not proof_b64:
|
||||
return
|
||||
try:
|
||||
proof_raw = base64.b64decode(proof_b64, validate=True)
|
||||
except (ValueError, base64.binascii.Error):
|
||||
return
|
||||
mech = (self._sasl_mechanism or "").upper()
|
||||
if "SHA-256" in mech or "SHA256" in mech:
|
||||
kind = "scram_sha256"
|
||||
elif "SHA-1" in mech or "SHA1" in mech:
|
||||
kind = "scram_sha1"
|
||||
else:
|
||||
kind = "scram_unknown"
|
||||
_log("auth", src=self._peer[0],
|
||||
username=self._sasl_username or "",
|
||||
principal=self._sasl_username,
|
||||
mechanism=self._sasl_mechanism or "",
|
||||
secret_kind=kind,
|
||||
secret_printable=proof_b64,
|
||||
secret_b64=base64.b64encode(proof_raw).decode("ascii"))
|
||||
return
|
||||
|
||||
def connection_lost(self, exc):
|
||||
_log("disconnect", src=self._peer[0] if self._peer else "?")
|
||||
|
||||
|
||||
async def main():
|
||||
_log("startup", msg=f"MongoDB server starting as {NODE_NAME}")
|
||||
loop = asyncio.get_running_loop()
|
||||
server = await loop.create_server(MongoDBProtocol, "0.0.0.0", PORT) # nosec B104
|
||||
async with server:
|
||||
await server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
261
decnet/templates/mongodb/syslog_bridge.py
Normal file
261
decnet/templates/mongodb/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