Files
shopdb-flask/plugins/endpoints/api/agentauth.py
cproudlock 70d5531b4d Make rollback, first upgrades and pin changes work as tested on Windows
Found in an end-to-end test on a Windows 11 VM against a self-signed server.

- Rollback: a 1.20 agent re-enrolls within a second of an un-enroll, so an
  older agent pushed afterwards arrived on an enrolled PC and was refused.
  Revoke now takes {"blockreenroll": true, "reason": ...}; a blocked PC is
  never issued a credential and keeps working on the shared key until
  POST .../assets/<assetid>/allow-reenroll. The Enrollment page offers the
  block when un-enrolling and shows blocked PCs with an allow button.
- First upgrade of old agents: agents before 1.20 check the server
  certificate when downloading the upgrade, so a store wave failed on PCs that
  do not trust a self-signed server while the Migration tab said ready. A
  failed download now marks the PC blocked with "server certificate not
  trusted by this PC". New Install-ShopDBServerCertificate.ps1 (GE-Enforce,
  SYSTEM) adds a non-CA server certificate to the trusted roots after checking
  its thumbprint; the server certificate page offers a .cer download and the
  SHA-1 thumbprint.
- The generated installer writes ServerPins (with an optional next pin for a
  planned rotation), can leave the shared key out so the PC waits for
  approval, never touches an existing credential, and skips the trusted-root
  import for a CA certificate.
- The agent re-reads server pins about every 60 seconds and recycles pooled
  connections within 2 minutes, so a pin change needs no restart.
- An alert can only be acknowledged by a PC it targets.
- A wave no longer counts a PC as failed after a later wave upgraded it.
- The scripts report a pin mismatch only when the pin really is missing, and
  otherwise log the real error.
- Runbook: trust step before the first wave, rollback order, pin re-read,
  verifying the pin against the live URL; agent contract updated.
2026-09-15 16:07:06 -04:00

211 lines
6.7 KiB
Python

"""Agent authentication: per-PC credentials, with the shared key as fallback.
Every agent-facing endpoints route authenticates through authenticate_agent()
and, when the route names a PC, binds the caller through bind_hostname().
X-Endpoint-Credential The PC's own secret. The server derives the asset from
it; a hostname or assetid in the request that names a
different asset is refused with ASSET_MISMATCH.
X-API-Key The shared fleet key (or a collector-scoped managed
token). Accepted only while
plugin.endpoints.sharedkeyallowed is on, and never for a
PC that holds an active credential. A PC blocked
from re-enrolling has no active credential, so an
older agent on it keeps working on the shared key.
Only the sha256 of a credential is stored. The full secret exists once, in the
enroll response.
"""
import hashlib
import hmac
import re
import secrets
from datetime import datetime, timedelta, timezone
from flask import g, request
from shopdb.api import (
db, Setting, error_response, ErrorCodes, collector_authorized,
)
CREDENTIAL_HEADER = 'X-Endpoint-Credential'
CREDENTIAL_PREFIX = 'sdbe_'
# sdbe_ + 43 chars base64url (32 random bytes, unpadded).
_CREDENTIAL_PATTERN = re.compile(r'^sdbe_[A-Za-z0-9_-]{43}$')
DISPLAY_PREFIX_LENGTH = 12
SHARED_KEY_SETTING = 'plugin.endpoints.sharedkeyallowed'
AUTO_ENROLL_SETTING = 'plugin.endpoints.autoenroll'
CODE_CREDENTIAL_INVALID = 'CREDENTIAL_INVALID'
CODE_SHARED_KEY_REFUSED = 'SHARED_KEY_REFUSED'
CODE_ASSET_MISMATCH = 'ASSET_MISMATCH'
AUTH_CREDENTIAL = 'credential'
AUTH_SHARED_KEY = 'sharedkey'
# lastusedat is a display value, not an audit trail: one write per 5 minutes
# per PC keeps the long-poll from turning every claim into an UPDATE.
_TOUCH_INTERVAL = timedelta(minutes=5)
def _naive_utcnow():
return datetime.now(timezone.utc).replace(tzinfo=None)
def generate_credential():
return CREDENTIAL_PREFIX + secrets.token_urlsafe(32)
def hash_credential(secret):
return hashlib.sha256(secret.encode('utf-8')).hexdigest()
def shared_key_allowed():
return Setting.get(SHARED_KEY_SETTING, default=True) is not False
def auto_enroll_enabled():
return Setting.get(AUTO_ENROLL_SETTING, default=True) is not False
def active_credential_for(assetid):
from ..models import EndpointCredential
if assetid is None:
return None
return (EndpointCredential.query
.filter(EndpointCredential.assetid == assetid,
EndpointCredential.revokedat.is_(None))
.first())
def reenroll_blocked(assetid):
"""True when an admin blocked this asset from enrolling again."""
from ..models import EndpointCredential
if assetid is None:
return False
return (EndpointCredential.query
.filter(EndpointCredential.assetid == assetid,
EndpointCredential.reenrollblocked.is_(True))
.first()) is not None
def resolve_credential(secret, touch=True):
"""Asset id for an active credential, else None."""
from ..models import EndpointCredential
if not secret or not _CREDENTIAL_PATTERN.match(secret):
return None
digest = hash_credential(secret)
row = EndpointCredential.query.filter_by(credentialhash=digest).first()
if row is None or row.revokedat is not None:
return None
if not hmac.compare_digest(row.credentialhash, digest):
return None
if touch:
now = _naive_utcnow()
if row.lastusedat is None or now - row.lastusedat >= _TOUCH_INTERVAL:
row.lastusedat = now
db.session.commit()
return row.assetid
def resolve_hostname(hostname):
"""Asset id of the one computer with this hostname (case-insensitive)."""
from plugins.computers.models import Computer
hostname = (hostname or '').strip()
if not hostname:
return None
computer = (Computer.query
.filter(db.func.lower(Computer.hostname) == hostname.lower())
.first())
return computer.assetid if computer is not None else None
def shared_key_refused_for(hostname):
"""True when the shared key may not report for this hostname."""
if not shared_key_allowed():
return True
assetid = resolve_hostname(hostname)
return assetid is not None and active_credential_for(assetid) is not None
def credential_invalid_response():
return error_response(
CODE_CREDENTIAL_INVALID,
'Endpoint credential is unknown or revoked; enroll again',
http_code=401)
def shared_key_refused_response():
return error_response(
CODE_SHARED_KEY_REFUSED,
'The shared key is not accepted for this endpoint; use its credential',
http_code=401)
def asset_mismatch_response():
return error_response(
CODE_ASSET_MISMATCH,
'The request names a different endpoint than the credential',
http_code=403)
def authenticate_agent():
"""Authorize an agent request. Returns None when authorized, else a response.
Sets g.agentauth ('credential' or 'sharedkey') and g.agentassetid (the
credential's asset, or None until bind_hostname resolves one).
"""
g.agentauth = None
g.agentassetid = None
secret = request.headers.get(CREDENTIAL_HEADER)
if secret:
assetid = resolve_credential(secret.strip())
if assetid is None:
return credential_invalid_response()
g.agentauth = AUTH_CREDENTIAL
g.agentassetid = assetid
return None
error = collector_authorized('endpoints')
if error is not None:
return error
if not shared_key_allowed():
return shared_key_refused_response()
g.agentauth = AUTH_SHARED_KEY
return None
def is_credential_caller():
return getattr(g, 'agentauth', None) == AUTH_CREDENTIAL
def bind_hostname(hostname):
"""The asset this request acts for. Returns (assetid, error_response).
Credential: the credential's asset; a hostname naming another asset is an
ASSET_MISMATCH, and a missing hostname is fine.
Shared key: the hostname's asset (None when absent or unknown, for the
route to answer); an enrolled PC is refused.
"""
hostname = (hostname or '').strip()
if is_credential_caller():
if hostname and resolve_hostname(hostname) != g.agentassetid:
return None, asset_mismatch_response()
return g.agentassetid, None
if not hostname:
return None, None
assetid = resolve_hostname(hostname)
if assetid is not None and active_credential_for(assetid) is not None:
return None, shared_key_refused_response()
g.agentassetid = assetid
return assetid, None