merge: testing → main (reconcile 2-week divergence)

This commit is contained in:
2026-04-28 18:36:00 -04:00
parent 499836c9e4
commit 862e4dbb31
1235 changed files with 160255 additions and 7996 deletions

View File

@@ -0,0 +1,23 @@
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 server.py /opt/server.py
COPY entrypoint.sh /entrypoint.sh
RUN chmod +x /entrypoint.sh
EXPOSE 161/udp
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"]

View File

@@ -0,0 +1,3 @@
#!/bin/bash
set -e
exec python3 /opt/server.py

View 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)

View File

@@ -0,0 +1,268 @@
#!/usr/bin/env python3
"""
SNMP server (UDP 161).
Parses SNMPv1/v2c GetRequest PDUs, logs the community string and OID list,
then responds with a GetResponse containing plausible system OID values.
Logs all requests as JSON.
"""
import asyncio
import os
import struct
from syslog_bridge import (
encode_secret,
forward_syslog,
syslog_line,
write_syslog_file,
)
NODE_NAME = os.environ.get("NODE_NAME", "switch")
SERVICE_NAME = "snmp"
LOG_TARGET = os.environ.get("LOG_TARGET", "")
SNMP_ARCHETYPE = os.environ.get("SNMP_ARCHETYPE", "default")
def _get_archetype_values() -> dict:
archetypes = {
"water_plant": {
"sysDescr": f"Linux {NODE_NAME} 4.19.0-18-amd64 #1 SMP Debian 4.19.208-1 (2021-09-29) x86_64",
"sysContact": "ICS Admin <ics-admin@plant.local>",
"sysName": NODE_NAME,
"sysLocation": "Water Treatment Facility — Pump Room B",
},
"factory": {
"sysDescr": "VxWorks 6.9 (Rockwell Automation Allen-Bradley ControlLogix 5580)",
"sysContact": "Factory Floor Support <support@factory.local>",
"sysName": NODE_NAME,
"sysLocation": "Factory Floor",
},
"substation": {
"sysDescr": "SEL Real-Time Automation Controller RTAC SEL-3555 firmware 1.9.7.0",
"sysContact": "Grid Ops <gridops@utility.local>",
"sysName": NODE_NAME,
"sysLocation": "Main Substation",
},
"hospital": {
"sysDescr": f"Linux {NODE_NAME} 5.10.0-21-amd64 #1 SMP Debian 5.10.162-1 x86_64",
"sysContact": "Medical IT <medit@hospital.local>",
"sysName": NODE_NAME,
"sysLocation": "ICU Ward 3",
},
"default": {
"sysDescr": f"Linux {NODE_NAME} 5.15.0-91-generic #101-Ubuntu SMP Tue Nov 14 13:30:08 UTC 2023 x86_64",
"sysContact": "admin@localhost",
"sysName": NODE_NAME,
"sysLocation": "Server Room",
}
}
return archetypes.get(SNMP_ARCHETYPE, archetypes["default"])
_arch = _get_archetype_values()
# OID value map — fake but plausible
_OID_VALUES = {
"1.3.6.1.2.1.1.1.0": _arch["sysDescr"],
"1.3.6.1.2.1.1.2.0": "1.3.6.1.4.1.8072.3.2.10",
"1.3.6.1.2.1.1.3.0": "12345678", # sysUpTime
"1.3.6.1.2.1.1.4.0": _arch["sysContact"],
"1.3.6.1.2.1.1.5.0": _arch["sysName"],
"1.3.6.1.2.1.1.6.0": _arch["sysLocation"],
"1.3.6.1.2.1.1.7.0": "72",
}
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_ber_length(data: bytes, pos: int):
if pos >= len(data):
raise ValueError("Unexpected end of data reading ASN.1 length")
b = data[pos]
if b < 0x80:
return b, pos + 1
n = b & 0x7f
if pos + 1 + n > len(data):
raise ValueError("BER length bytes truncated")
length = int.from_bytes(data[pos + 1:pos + 1 + n], "big")
return length, pos + 1 + n
def _decode_oid(data: bytes) -> str:
if not data:
return ""
first = data[0]
oid = [first // 40, first % 40]
val = 0
for b in data[1:]:
val = (val << 7) | (b & 0x7f)
if not (b & 0x80):
oid.append(val)
val = 0
return ".".join(map(str, oid))
def _encode_oid(oid_str: str) -> bytes:
parts = list(map(int, oid_str.split(".")))
if len(parts) < 2:
return b""
result = bytes([parts[0] * 40 + parts[1]])
for n in parts[2:]:
if n == 0:
result += b"\x00"
else:
encoded = []
while n:
encoded.append(n & 0x7f)
n >>= 7
encoded.reverse()
for i, b in enumerate(encoded):
result += bytes([b | (0x80 if i < len(encoded) - 1 else 0)])
return result
def _ber_tlv(tag: int, value: bytes) -> bytes:
length = len(value)
if length < 0x80:
return bytes([tag, length]) + value
elif length < 0x100:
return bytes([tag, 0x81, length]) + value
else:
return bytes([tag, 0x82]) + struct.pack(">H", length) + value
def _parse_snmp(data: bytes):
"""Return (version, community, request_id, oids) or raise."""
pos = 0
if len(data) == 0 or data[pos] != 0x30:
raise ValueError("Not a valid ASN.1 sequence")
pos += 1
_, pos = _read_ber_length(data, pos)
# version
if pos >= len(data) or data[pos] != 0x02:
raise ValueError("Expected SNMP version INTEGER")
pos += 1
v_len, pos = _read_ber_length(data, pos)
version = int.from_bytes(data[pos:pos + v_len], "big")
pos += v_len
# community
if pos >= len(data) or data[pos] != 0x04:
raise ValueError("Expected SNMP community OCTET STREAM")
pos += 1
c_len, pos = _read_ber_length(data, pos)
community = data[pos:pos + c_len].decode(errors="replace")
pos += c_len
# PDU type (0xa0 = GetRequest, 0xa1 = GetNextRequest)
if pos >= len(data):
raise ValueError("Missing PDU type")
pdu_type = data[pos]
if pdu_type not in (0xa0, 0xa1):
raise ValueError(f"Invalid PDU type {pdu_type}")
pos += 1
_, pos = _read_ber_length(data, pos)
# request-id
if pos >= len(data) or data[pos] != 0x02:
raise ValueError("Expected Request ID INTEGER")
pos += 1
r_len, pos = _read_ber_length(data, pos)
request_id = int.from_bytes(data[pos:pos + r_len], "big")
pos += r_len
# skip error-status
if pos >= len(data) or data[pos] != 0x02:
raise ValueError("Expected error-status INTEGER")
pos += 1
e_len, pos = _read_ber_length(data, pos)
pos += e_len
# skip error-index
if pos >= len(data) or data[pos] != 0x02:
raise ValueError("Expected error-index INTEGER")
pos += 1
i_len, pos = _read_ber_length(data, pos)
pos += i_len
# varbind list
if pos >= len(data) or data[pos] != 0x30:
raise ValueError("Expected varbind list SEQUENCE")
pos += 1
vbl_len, pos = _read_ber_length(data, pos)
end = pos + vbl_len
oids = []
while pos < end:
if data[pos] != 0x30:
raise ValueError("Expected varbind SEQUENCE")
pos += 1
vb_len, pos = _read_ber_length(data, pos)
if data[pos] != 0x06:
raise ValueError("Expected Object Identifier")
pos += 1
oid_len, pos = _read_ber_length(data, pos)
oid = _decode_oid(data[pos:pos + oid_len])
pos += oid_len
oids.append(oid)
pos += vb_len - oid_len - 2 # skip value
return version, community, request_id, oids
def _build_response(version: int, community: str, request_id: int, oids: list) -> bytes:
varbinds = b""
for oid in oids:
oid_enc = _encode_oid(oid)
value_str = _OID_VALUES.get(oid, "")
oid_tlv = _ber_tlv(0x06, oid_enc)
val_tlv = _ber_tlv(0x04, value_str.encode())
varbinds += _ber_tlv(0x30, oid_tlv + val_tlv)
varbind_list = _ber_tlv(0x30, varbinds)
req_id_tlv = _ber_tlv(0x02, request_id.to_bytes(4, "big"))
error_status = _ber_tlv(0x02, b"\x00")
error_index = _ber_tlv(0x02, b"\x00")
pdu = _ber_tlv(0xa2, req_id_tlv + error_status + error_index + varbind_list)
ver_tlv = _ber_tlv(0x02, version.to_bytes(1, "big"))
comm_tlv = _ber_tlv(0x04, community.encode())
return _ber_tlv(0x30, ver_tlv + comm_tlv + pdu)
class SNMPProtocol(asyncio.DatagramProtocol):
def __init__(self):
self._transport = None
def connection_made(self, transport):
self._transport = transport
def datagram_received(self, data, addr):
try:
version, community, request_id, oids = _parse_snmp(data)
# SNMP v1/v2c community is the only auth mechanism on the wire
# — every packet carries the shared secret in plaintext. Land
# it as a Credential row keyed `snmp_community` so reuse-
# analytics treats community-string spray as the same shape
# of attack signal as cleartext password spray.
_log("get_request", src=addr[0], src_port=addr[1],
version=version, community=community, oids=oids,
principal=None, secret_kind="snmp_community",
**encode_secret(community))
response = _build_response(version, community, request_id, oids)
self._transport.sendto(response, addr)
except Exception as e:
_log("parse_error", severity=4, src=addr[0], error=str(e), data=data[:64].hex())
def error_received(self, exc):
pass
async def main():
_log("startup", msg=f"SNMP server starting as {NODE_NAME} with archetype {SNMP_ARCHETYPE}")
loop = asyncio.get_running_loop()
transport, _ = await loop.create_datagram_endpoint(
SNMPProtocol, local_addr=("0.0.0.0", 161) # nosec B104
)
try:
await asyncio.sleep(float("inf"))
finally:
transport.close()
if __name__ == "__main__":
asyncio.run(main())

View 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