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

decnet/templates/conpot/Dockerfile

@@ -0,0 +1,28 @@
+ARG BASE_IMAGE=honeynet/conpot:latest
+FROM ${BASE_IMAGE}
+
+USER root
+
+# Replace 5020 with 502 in all templates so Modbus binds on the standard port
+RUN find /opt /usr /etc /home -name "*.xml" -exec sed -i 's/<port>5020<\/port>/<port>502<\/port>/g' {} + 2>/dev/null || true
+RUN find /opt /usr /etc /home -name "*.xml" -exec sed -i 's/port="5020"/port="502"/g' {} + 2>/dev/null || true
+
+# Install libcap and give the Python interpreter permission to bind ports < 1024
+RUN (apt-get update && apt-get install -y --no-install-recommends libcap2-bin 2>/dev/null) || (apk add --no-cache libcap 2>/dev/null) || true
+RUN find /home/conpot/.local/bin /usr /opt -type f -name 'python*' -exec setcap 'cap_net_bind_service+eip' {} \; 2>/dev/null || true
+
+# Bridge conpot's own logger into syslog-relay's RFC 5424 syslog pipeline.
+# entrypoint.py is self-contained (inlines the formatter) because the
+# conpot base image runs Python 3.6, which cannot import the shared
+# syslog_bridge.py (that file uses 3.9+ / 3.10+ type syntax).
+COPY entrypoint.py /home/conpot/entrypoint.py
+RUN chown conpot:conpot /home/conpot/entrypoint.py \
+    && chmod +x /home/conpot/entrypoint.py
+
+# The upstream image already runs as non-root 'conpot'.
+# We do NOT switch to a 'logrelay' user — doing so breaks pkg_resources
+# because conpot's eggs live under /home/conpot/.local and are only on
+# the Python path for that user.
+USER conpot
+
+ENTRYPOINT ["/usr/bin/python3", "/home/conpot/entrypoint.py"]

decnet/templates/conpot/entrypoint.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Entrypoint wrapper for the Conpot ICS/SCADA honeypot.
+
+Launches conpot as a child process and bridges its log output into the
+syslog-relay structured syslog pipeline.  Each line from conpot stdout/stderr
+is classified and emitted as an RFC 5424 syslog line so the host-side
+collector can ingest it alongside every other service.
+
+Written to be compatible with Python 3.6 (the conpot base image version).
+"""
+from __future__ import print_function
+
+import os
+import re
+import signal
+import subprocess
+import sys
+from datetime import datetime, timezone
+
+# ── RFC 5424 inline formatter (Python 3.6-compatible) ─────────────────────────
+
+_FACILITY_LOCAL0 = 16
+_SD_ID = "relay@55555"
+_NILVALUE = "-"
+
+SEVERITY_INFO    = 6
+SEVERITY_WARNING = 4
+SEVERITY_ERROR   = 3
+
+
+def _sd_escape(value):
+    return value.replace("\\", "\\\\").replace('"', '\\"').replace("]", "\\]")
+
+
+def _syslog_line(event_type, severity=SEVERITY_INFO, **fields):
+    pri     = "<{}>".format(_FACILITY_LOCAL0 * 8 + severity)
+    ts      = datetime.now(timezone.utc).isoformat()
+    host    = NODE_NAME[:255]
+    appname = "conpot"
+    msgid   = event_type[:32]
+
+    if fields:
+        params = " ".join('{}="{}"'.format(k, _sd_escape(str(v))) for k, v in fields.items())
+        sd = "[{} {}]".format(_SD_ID, params)
+    else:
+        sd = _NILVALUE
+
+    return "{pri}1 {ts} {host} {appname} {nil} {msgid} {sd}".format(
+        pri=pri, ts=ts, host=host, appname=appname,
+        nil=_NILVALUE, msgid=msgid, sd=sd,
+    )
+
+
+def _log(event_type, severity=SEVERITY_INFO, **fields):
+    print(_syslog_line(event_type, severity, **fields), flush=True)
+
+
+# ── Config ────────────────────────────────────────────────────────────────────
+
+NODE_NAME = os.environ.get("NODE_NAME", "conpot-node")
+TEMPLATE  = os.environ.get("CONPOT_TEMPLATE", "default")
+
+_CONPOT_CMD = [
+    "/home/conpot/.local/bin/conpot",
+    "--template", TEMPLATE,
+    "--logfile", "/var/log/conpot/conpot.log",
+    "-f",
+    "--temp_dir", "/tmp",
+]
+
+# Grab the first routable IPv4 address from a log line
+_IP_RE = re.compile(r"\b((?!127\.)(?!0\.)(?!255\.)\d{1,3}(?:\.\d{1,3}){3})\b")
+
+_REQUEST_RE = re.compile(
+    r"request|recv|received|connect|session|query|command|"
+    r"modbus|snmp|http|s7comm|bacnet|enip",
+    re.IGNORECASE,
+)
+_ERROR_RE   = re.compile(r"error|exception|traceback|critical|fail", re.IGNORECASE)
+_WARN_RE    = re.compile(r"warning|warn", re.IGNORECASE)
+_STARTUP_RE = re.compile(
+    r"starting|started|listening|server|initializ|template|conpot",
+    re.IGNORECASE,
+)
+
+
+# ── Classifier ────────────────────────────────────────────────────────────────
+
+def _classify(raw):
+    """Return (event_type, severity, fields) for one conpot log line."""
+    fields = {}
+
+    m = _IP_RE.search(raw)
+    if m:
+        fields["src"] = m.group(1)
+
+    fields["msg"] = raw[:300]
+
+    if _ERROR_RE.search(raw):
+        return "error", SEVERITY_ERROR, fields
+    if _WARN_RE.search(raw):
+        return "warning", SEVERITY_WARNING, fields
+    if _REQUEST_RE.search(raw):
+        return "request", SEVERITY_INFO, fields
+    if _STARTUP_RE.search(raw):
+        return "startup", SEVERITY_INFO, fields
+    return "log", SEVERITY_INFO, fields
+
+
+# ── Main ──────────────────────────────────────────────────────────────────────
+
+def main():
+    _log("startup", msg="Conpot ICS honeypot starting (template={})".format(TEMPLATE))
+
+    proc = subprocess.Popen(
+        _CONPOT_CMD,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        bufsize=1,
+        universal_newlines=True,
+    )
+
+    def _forward(sig, _frame):
+        proc.send_signal(sig)
+
+    signal.signal(signal.SIGTERM, _forward)
+    signal.signal(signal.SIGINT, _forward)
+
+    try:
+        for raw_line in proc.stdout:
+            line = raw_line.rstrip()
+            if not line:
+                continue
+            event_type, severity, fields = _classify(line)
+            _log(event_type, severity, **fields)
+    finally:
+        proc.wait()
+        _log("shutdown", msg="Conpot ICS honeypot stopped")
+        sys.exit(proc.returncode)
+
+
+if __name__ == "__main__":
+    main()

decnet/templates/conpot/instance_seed.py

@@ -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)

decnet/templates/conpot/syslog_bridge.py

@@ -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