merge: testing → main (reconcile 2-week divergence)
This commit is contained in:
24
decnet/templates/redis/Dockerfile
Normal file
24
decnet/templates/redis/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 6379
|
||||
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/redis/entrypoint.sh
Normal file
3
decnet/templates/redis/entrypoint.sh
Normal file
@@ -0,0 +1,3 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
exec python3 /opt/server.py
|
||||
120
decnet/templates/redis/instance_seed.py
Normal file
120
decnet/templates/redis/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)
|
||||
333
decnet/templates/redis/server.py
Normal file
333
decnet/templates/redis/server.py
Normal file
@@ -0,0 +1,333 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Redisserver.
|
||||
Implements enough of the RESP protocol to respond to AUTH, INFO, CONFIG GET,
|
||||
KEYS, and arbitrary commands. Logs every command and argument as JSON.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
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", "cache-server")
|
||||
SERVICE_NAME = "redis"
|
||||
LOG_TARGET = os.environ.get("LOG_TARGET", "")
|
||||
PORT = int(os.environ.get("PORT", "6379"))
|
||||
|
||||
# Per-instance realistic version pick (weighted toward still-supported lines).
|
||||
_REDIS_VER = os.environ.get("REDIS_VERSION") or _seed.pick_weighted([
|
||||
("7.2.4", 2), ("7.2.5", 3), ("7.2.6", 3), ("7.2.7", 2),
|
||||
("7.0.15", 2), ("7.0.14", 1),
|
||||
("6.2.14", 2), ("6.2.16", 1),
|
||||
])
|
||||
# Kernel line matching plausible Debian/Ubuntu LTS minor ranges.
|
||||
_REDIS_OS = os.environ.get("REDIS_OS") or _seed.pick([
|
||||
"Linux 5.15.0-118-generic x86_64",
|
||||
"Linux 6.1.0-21-amd64 x86_64",
|
||||
"Linux 5.10.0-30-amd64 x86_64",
|
||||
"Linux 6.5.0-27-generic x86_64",
|
||||
])
|
||||
_RUN_ID = _seed.instance_hex(20, "redis-run")
|
||||
_PROCESS_ID = _seed.rng.randint(120, 32000)
|
||||
_TCP_PORT_STR = str(PORT)
|
||||
|
||||
# AUTH config: empty REDIS_PASSWORD means "no auth configured" — AUTH returns
|
||||
# the canonical "Client sent AUTH, but no password is set" error, matching a
|
||||
# real redis-server with requirepass unset.
|
||||
_REQUIREPASS = os.environ.get("REDIS_PASSWORD", "")
|
||||
|
||||
|
||||
def _info_block() -> bytes:
|
||||
uptime = _seed.uptime_seconds()
|
||||
uptime_days = max(1, uptime // 86400)
|
||||
# Minimal but plausible subset; real redis INFO has ~150 keys.
|
||||
text = (
|
||||
"# Server\r\n"
|
||||
f"redis_version:{_REDIS_VER}\r\n"
|
||||
f"redis_git_sha1:00000000\r\n"
|
||||
f"redis_git_dirty:0\r\n"
|
||||
f"redis_build_id:{_seed.instance_hex(8, 'redis-build')}\r\n"
|
||||
"redis_mode:standalone\r\n"
|
||||
f"os:{_REDIS_OS}\r\n"
|
||||
"arch_bits:64\r\n"
|
||||
f"process_id:{_PROCESS_ID}\r\n"
|
||||
f"run_id:{_RUN_ID}\r\n"
|
||||
f"tcp_port:{_TCP_PORT_STR}\r\n"
|
||||
f"uptime_in_seconds:{uptime}\r\n"
|
||||
f"uptime_in_days:{uptime_days}\r\n"
|
||||
"hz:10\r\n"
|
||||
"# Clients\r\n"
|
||||
"connected_clients:1\r\n"
|
||||
"maxclients:10000\r\n"
|
||||
"# Memory\r\n"
|
||||
f"used_memory:{_seed.rng.randint(800_000, 12_000_000)}\r\n"
|
||||
"mem_fragmentation_ratio:1.12\r\n"
|
||||
"# Stats\r\n"
|
||||
f"total_connections_received:{_seed.rng.randint(50, 9000)}\r\n"
|
||||
f"total_commands_processed:{_seed.rng.randint(5_000, 2_000_000)}\r\n"
|
||||
"# Keyspace\r\n"
|
||||
)
|
||||
return text.encode()
|
||||
|
||||
|
||||
def _build_fake_store() -> dict[bytes, bytes]:
|
||||
"""Per-instance plausible cache content. No embedded DECNET-identifying
|
||||
strings; keys / values shaped like what real apps leave in redis."""
|
||||
n_sessions = _seed.rng.randint(3, 14)
|
||||
store: dict[bytes, bytes] = {}
|
||||
app_slug = _seed.pick(["api", "web", "worker", "shop", "admin", "cms"])
|
||||
env_slug = _seed.pick(["prod", "stage", "live"])
|
||||
for i in range(n_sessions):
|
||||
sid = _seed.instance_hex(16, f"sess-{i}")
|
||||
uid = _seed.rng.randint(1000, 999_999)
|
||||
store[f"session:{sid}".encode()] = (
|
||||
f'{{"uid":{uid},"exp":{int(_seed.boot_epoch()) + 86400 * 7}}}'
|
||||
).encode()
|
||||
for i in range(_seed.rng.randint(2, 6)):
|
||||
store[f"cache:{app_slug}:feed:{i}".encode()] = (
|
||||
_seed.instance_hex(24, f"feed-{i}").encode()
|
||||
)
|
||||
store[f"stats:{app_slug}:{env_slug}:requests".encode()] = (
|
||||
str(_seed.rng.randint(5_000, 900_000)).encode()
|
||||
)
|
||||
return store
|
||||
|
||||
|
||||
_FAKE_STORE = _build_fake_store()
|
||||
|
||||
# Config presented via CONFIG GET — realistic subset of a default redis.conf.
|
||||
_CONFIG = {
|
||||
"maxmemory": "0",
|
||||
"maxmemory-policy": "noeviction",
|
||||
"maxclients": "10000",
|
||||
"timeout": "0",
|
||||
"tcp-keepalive": "300",
|
||||
"databases": "16",
|
||||
"save": "3600 1 300 100 60 10000",
|
||||
"appendonly": "no",
|
||||
"loglevel": "notice",
|
||||
"dir": "/var/lib/redis",
|
||||
"bind": "127.0.0.1 -::1",
|
||||
"protected-mode": "yes",
|
||||
"supervised": "systemd",
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
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 _bulk(s: str) -> bytes:
|
||||
enc = s.encode()
|
||||
return f"${len(enc)}\r\n".encode() + enc + b"\r\n"
|
||||
|
||||
|
||||
def _err(msg: str) -> bytes:
|
||||
return f"-ERR {msg}\r\n".encode()
|
||||
|
||||
|
||||
class RESPParser:
|
||||
"""Incremental RESP array parser — returns list of str tokens or None if incomplete."""
|
||||
|
||||
def __init__(self):
|
||||
self._buf = b""
|
||||
|
||||
def feed(self, data: bytes):
|
||||
self._buf += data
|
||||
return self._try_parse()
|
||||
|
||||
def _try_parse(self):
|
||||
commands = []
|
||||
while self._buf:
|
||||
cmd, consumed = self._parse_one(self._buf)
|
||||
if cmd is None:
|
||||
break
|
||||
commands.append(cmd)
|
||||
self._buf = self._buf[consumed:]
|
||||
return commands
|
||||
|
||||
def _parse_one(self, buf: bytes):
|
||||
if not buf:
|
||||
return None, 0
|
||||
if buf[0:1] == b"*":
|
||||
end = buf.find(b"\r\n")
|
||||
if end == -1:
|
||||
return None, 0
|
||||
count = int(buf[1:end])
|
||||
pos = end + 2
|
||||
parts = []
|
||||
for _ in range(count):
|
||||
if pos >= len(buf):
|
||||
return None, 0
|
||||
if buf[pos:pos + 1] != b"$":
|
||||
return None, 0
|
||||
end2 = buf.find(b"\r\n", pos)
|
||||
if end2 == -1:
|
||||
return None, 0
|
||||
length = int(buf[pos + 1:end2])
|
||||
start = end2 + 2
|
||||
if start + length + 2 > len(buf):
|
||||
return None, 0
|
||||
parts.append(buf[start:start + length].decode(errors="replace"))
|
||||
pos = start + length + 2
|
||||
return parts, pos
|
||||
# Inline command
|
||||
end = buf.find(b"\r\n")
|
||||
if end == -1:
|
||||
end = buf.find(b"\n")
|
||||
if end == -1:
|
||||
return None, 0
|
||||
line = buf[:end].decode(errors="replace").strip()
|
||||
return line.split(), end + (2 if buf[end:end + 2] == b"\r\n" else 1)
|
||||
|
||||
|
||||
def _config_get(pattern: str) -> bytes:
|
||||
"""Emulate `CONFIG GET <pattern>` — returns alternating key/value bulks."""
|
||||
import fnmatch
|
||||
matches = [(k, v) for k, v in _CONFIG.items() if fnmatch.fnmatchcase(k, pattern)]
|
||||
out = f"*{len(matches) * 2}\r\n".encode()
|
||||
for k, v in matches:
|
||||
out += _bulk(k) + _bulk(v)
|
||||
return out
|
||||
|
||||
|
||||
class RedisProtocol(asyncio.Protocol):
|
||||
def __init__(self):
|
||||
self._transport = None
|
||||
self._peer = None
|
||||
self._parser = RESPParser()
|
||||
self._authed = not _REQUIREPASS # auth satisfied iff no password set
|
||||
|
||||
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):
|
||||
for cmd in self._parser.feed(data):
|
||||
self._handle_command(cmd)
|
||||
|
||||
def _write(self, payload: bytes) -> None:
|
||||
"""Writes with per-response jitter. Unseeded so two connections to
|
||||
the same decky don't get an identical latency fingerprint. Honeypot
|
||||
throughput targets are low; a few ms of blocking sleep here is fine
|
||||
and avoids the asyncio-task plumbing the synchronous protocol model
|
||||
doesn't otherwise need."""
|
||||
_seed.jitter_sync(2, 40)
|
||||
if self._transport and not self._transport.is_closing():
|
||||
self._transport.write(payload)
|
||||
|
||||
def _handle_command(self, parts):
|
||||
if not parts:
|
||||
return
|
||||
verb = parts[0].upper()
|
||||
args = parts[1:]
|
||||
_log("command", src=self._peer[0], cmd=verb, args=args[:8])
|
||||
|
||||
if verb == "AUTH":
|
||||
# Redis 6+ accepts two-arg AUTH (`AUTH <user> <pw>`) for ACL
|
||||
# auth; legacy single-arg AUTH is just the password. Capture
|
||||
# the username when present so attackers brute-forcing ACLs
|
||||
# leave the same trail SSH/FTP do.
|
||||
password = args[-1] if args else ""
|
||||
_user = args[0] if len(args) >= 2 else None
|
||||
_log("auth", src=self._peer[0],
|
||||
principal=_user, **encode_secret(password))
|
||||
if not _REQUIREPASS:
|
||||
self._write(
|
||||
_err("Client sent AUTH, but no password is set. "
|
||||
"Did you mean AUTH <username> <password>?")
|
||||
)
|
||||
elif password == _REQUIREPASS:
|
||||
self._authed = True
|
||||
self._write(b"+OK\r\n")
|
||||
else:
|
||||
self._write(_err("WRONGPASS invalid username-password pair or user is disabled."))
|
||||
return
|
||||
if not self._authed:
|
||||
self._write(_err("NOAUTH Authentication required."))
|
||||
return
|
||||
if verb == "INFO":
|
||||
info = _info_block()
|
||||
self._write(f"${len(info)}\r\n".encode() + info + b"\r\n")
|
||||
elif verb == "PING":
|
||||
self._write(b"+PONG\r\n")
|
||||
elif verb == "CONFIG":
|
||||
sub = args[0].upper() if args else ""
|
||||
if sub == "GET" and len(args) >= 2:
|
||||
self._write(_config_get(args[1]))
|
||||
elif sub == "SET":
|
||||
self._write(b"+OK\r\n")
|
||||
elif sub == "RESETSTAT":
|
||||
self._write(b"+OK\r\n")
|
||||
else:
|
||||
self._write(_err(
|
||||
"Unknown CONFIG subcommand or wrong number of arguments for '"
|
||||
f"{sub.lower() or '?'}'"
|
||||
))
|
||||
elif verb == "KEYS":
|
||||
pattern = args[0] if args else "*"
|
||||
keys = list(_FAKE_STORE.keys())
|
||||
if pattern.endswith('*') and pattern != '*':
|
||||
prefix = pattern[:-1].encode()
|
||||
keys = [k for k in keys if k.startswith(prefix)]
|
||||
elif pattern != '*':
|
||||
pat = pattern.encode()
|
||||
keys = [k for k in keys if k == pat]
|
||||
|
||||
resp = f"*{len(keys)}\r\n".encode() + b"".join(_bulk(k.decode()) for k in keys)
|
||||
self._write(resp)
|
||||
elif verb == "GET":
|
||||
key = args[0].encode() if args else b""
|
||||
if key in _FAKE_STORE:
|
||||
self._write(_bulk(_FAKE_STORE[key].decode()))
|
||||
else:
|
||||
self._write(b"$-1\r\n")
|
||||
elif verb == "SCAN":
|
||||
keys = list(_FAKE_STORE.keys())
|
||||
resp = b"*2\r\n$1\r\n0\r\n" + f"*{len(keys)}\r\n".encode() + b"".join(_bulk(k.decode()) for k in keys)
|
||||
self._write(resp)
|
||||
elif verb == "TYPE":
|
||||
self._write(b"+string\r\n")
|
||||
elif verb == "TTL":
|
||||
self._write(b":-1\r\n")
|
||||
elif verb == "DBSIZE":
|
||||
self._write(f":{len(_FAKE_STORE)}\r\n".encode())
|
||||
elif verb == "COMMAND":
|
||||
self._write(b"*0\r\n")
|
||||
elif verb == "CLIENT":
|
||||
self._write(b"+OK\r\n")
|
||||
elif verb == "SELECT":
|
||||
self._write(b"+OK\r\n")
|
||||
elif verb == "QUIT":
|
||||
self._write(b"+OK\r\n")
|
||||
if self._transport:
|
||||
self._transport.close()
|
||||
else:
|
||||
self._write(_err(f"unknown command '{verb.lower()}'"))
|
||||
|
||||
def connection_lost(self, exc):
|
||||
_log("disconnect", src=self._peer[0] if self._peer else "?")
|
||||
|
||||
|
||||
async def main():
|
||||
_log("startup", msg=f"Redis server starting as {NODE_NAME}")
|
||||
loop = asyncio.get_running_loop()
|
||||
server = await loop.create_server(RedisProtocol, "0.0.0.0", PORT) # nosec B104
|
||||
async with server:
|
||||
await server.serve_forever()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
261
decnet/templates/redis/syslog_bridge.py
Normal file
261
decnet/templates/redis/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