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

decnet/templates/ldap/Dockerfile

@@ -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 389 636
+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"]

decnet/templates/ldap/entrypoint.sh

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

decnet/templates/ldap/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/ldap/server.py

@@ -0,0 +1,208 @@
+#!/usr/bin/env python3
+"""
+LDAPserver.
+Parses BER-encoded BindRequest messages, logs DN and password, returns an
+invalidCredentials error. Logs all interactions as JSON.
+"""
+
+import asyncio
+import os
+import re
+
+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", "ldapserver")
+SERVICE_NAME   = "ldap"
+LOG_TARGET = os.environ.get("LOG_TARGET", "")
+
+# RFC 4514 distinguished-name grammar: DN is a sequence of comma-separated
+# RDNs like "cn=foo,ou=people,dc=example,dc=com". Each RDN is
+# attribute=value, attribute matches [A-Za-z][A-Za-z0-9-]*. We keep this
+# check loose on value contents (commas can be escaped etc.) but tight on
+# shape, so garbage like `"abc"` or `\x00\x00` gets rejected with
+# invalidDNSyntax (34) instead of invalidCredentials (49) — that's how a
+# real OpenLDAP replies.
+_RDN_RE = re.compile(r"^[A-Za-z][A-Za-z0-9-]*=.+$")
+
+
+def _is_valid_dn(dn: str) -> bool:
+    """True for empty (anonymous bind) or RFC 4514-shaped DN."""
+    if dn == "":
+        return True
+    if len(dn) > 1024:
+        return False
+    # Split on unescaped commas. Not perfect, but catches the obvious
+    # "not a DN" inputs (missing '=' in some RDN, empty segments, etc.).
+    parts: list[str] = []
+    buf = ""
+    escape = False
+    for ch in dn:
+        if escape:
+            buf += ch
+            escape = False
+            continue
+        if ch == "\\":
+            buf += ch
+            escape = True
+            continue
+        if ch == ",":
+            parts.append(buf)
+            buf = ""
+            continue
+        buf += ch
+    parts.append(buf)
+    return all(_RDN_RE.match(p.strip()) for p in parts)
+
+
+
+
+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 _ber_length(data: bytes, pos: int):
+    """Return (length, next_pos)."""
+    b = data[pos]
+    if b < 0x80:
+        return b, pos + 1
+    n = b & 0x7f
+    length = int.from_bytes(data[pos + 1:pos + 1 + n], "big")
+    return length, pos + 1 + n
+
+
+def _ber_string(data: bytes, pos: int):
+    """Skip tag byte, read BER length, return (string, next_pos)."""
+    pos += 1  # skip tag
+    length, pos = _ber_length(data, pos)
+    return data[pos:pos + length].decode(errors="replace"), pos + length
+
+
+def _parse_bind_request(msg: bytes):
+    """Best-effort extraction of (dn, password) from a raw LDAPMessage."""
+    try:
+        pos = 0
+        # LDAPMessage SEQUENCE
+        assert msg[pos] == 0x30  # nosec B101
+        pos += 1
+        _, pos = _ber_length(msg, pos)
+        # messageID INTEGER
+        assert msg[pos] == 0x02  # nosec B101
+        pos += 1
+        id_len, pos = _ber_length(msg, pos)
+        pos += id_len
+        # BindRequest [APPLICATION 0]
+        assert msg[pos] == 0x60  # nosec B101
+        pos += 1
+        _, pos = _ber_length(msg, pos)
+        # version INTEGER
+        assert msg[pos] == 0x02  # nosec B101
+        pos += 1
+        v_len, pos = _ber_length(msg, pos)
+        pos += v_len
+        # name LDAPDN (OCTET STRING)
+        dn, pos = _ber_string(msg, pos)
+        # authentication CHOICE — simple [0] OCTET STRING
+        if msg[pos] == 0x80:
+            pos += 1
+            pw_len, pos = _ber_length(msg, pos)
+            password = msg[pos:pos + pw_len].decode(errors="replace")
+        else:
+            password = "<sasl_or_unknown>"  # nosec B105
+        return dn, password
+    except Exception:
+        return "<parse_error>", "<parse_error>"
+
+
+def _bind_error_response(message_id: int, result_code: int = 49, error_text: str = "") -> bytes:
+    """BindResponse with a configurable resultCode + diagnosticMessage.
+    49 = invalidCredentials, 34 = invalidDNSyntax, 53 = unwillingToPerform."""
+    err_bytes = error_text.encode()
+    result_enc = bytes([0x0a, 0x01, result_code & 0xff])
+    matched_dn = bytes([0x04, 0x00])
+    error_msg  = bytes([0x04, len(err_bytes)]) + err_bytes
+    bind_resp_body = result_enc + matched_dn + error_msg
+    bind_resp = bytes([0x61, len(bind_resp_body)]) + bind_resp_body
+
+    msg_id_enc = bytes([0x02, 0x01, message_id & 0xff])
+    ldap_msg_body = msg_id_enc + bind_resp
+    return bytes([0x30, len(ldap_msg_body)]) + ldap_msg_body
+
+
+class LDAPProtocol(asyncio.Protocol):
+    def __init__(self):
+        self._transport = None
+        self._peer = None
+        self._buf = b""
+
+    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
+        self._process()
+
+    def _process(self):
+        while len(self._buf) >= 2:
+            if self._buf[0] != 0x30:
+                self._buf = b""
+                return
+            if self._buf[1] < 0x80:
+                msg_len = self._buf[1] + 2
+            elif self._buf[1] == 0x81:
+                if len(self._buf) < 3:
+                    return
+                msg_len = self._buf[2] + 3
+            else:
+                self._buf = b""
+                return
+            if len(self._buf) < msg_len:
+                return
+            msg = self._buf[:msg_len]
+            self._buf = self._buf[msg_len:]
+            self._handle_message(msg)
+
+    def _handle_message(self, msg: bytes):
+        # Extract messageID for the response
+        try:
+            message_id = msg[4] if len(msg) > 4 else 1
+        except Exception:
+            message_id = 1
+        dn, password = _parse_bind_request(msg)
+        _log("bind", src=self._peer[0], dn=dn, principal=dn,
+             **encode_secret(password))
+        _seed.jitter_sync(10, 60)
+        if dn and not _is_valid_dn(dn):
+            # OpenLDAP returns invalidDNSyntax (34) for malformed DNs, with
+            # a diagnostic like: "invalid DN syntax". Matching that exactly
+            # keeps the decoy consistent with what a scanner expects.
+            self._transport.write(_bind_error_response(
+                message_id, result_code=34,
+                error_text="invalid DN"
+            ))
+        else:
+            self._transport.write(_bind_error_response(message_id))
+
+    def connection_lost(self, exc):
+        _log("disconnect", src=self._peer[0] if self._peer else "?")
+
+
+async def main():
+    _log("startup", msg=f"LDAP server starting as {NODE_NAME}")
+    loop = asyncio.get_running_loop()
+    server = await loop.create_server(LDAPProtocol, "0.0.0.0", 389)  # nosec B104
+    async with server:
+        await server.serve_forever()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

decnet/templates/ldap/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