Compare commits

..
Author SHA1 Message Date
ChuckBuilds fc6104f229 fix(web): stop /config/main handing out every credential it holds
The endpoint returned the raw config to anyone who could reach the port, and
this web interface has no authentication of any kind. An unauthenticated
request against a live rig returned:

    github.api_token                40 chars
    incoming-packages.ha_token     183 chars
    jellyfin-now-playing.api_key    32 chars
    ledmatrix-weather.api_key       32 chars
    on-air.mqtt_password             8 chars
    youtube.api_key                 20 chars
    youtube-stats.api_key           39 chars

A GitHub token and a Home Assistant long-lived token among them. Anything on
that LAN could read them.

The x-secret masking the plugin config endpoints use does not reach here: this
route never consults a schema, and core keys such as github.api_token have no
schema to carry the marker. Several of the fields above *are* tagged x-secret
in their plugin's schema and were still returned in full, which is what rules
out the schema route as the fix for this endpoint.

Credential-named fields are now blanked. Matching on the name is blunt, and
for a whole-config dump that is the right default: anything named like a
credential should not leave the process, and a new plugin adding a
differently-shaped secret is covered without anyone remembering to tag it.

Blanked rather than removed, and safe to blank: POST /config/main merges into
the freshly loaded config and writes only the keys it was given, so a client
that round-trips this response cannot erase a secret it never saw. The web API
suites confirm it -- 81 passing, unchanged.

On the test that matters: the first version of this suite exercised the two
helpers and nothing else, and reverting the single line that wires the
redactor into the route passed all thirty of them. A property asserted on a
helper is not a property asserted on the endpoint, and it is the endpoint that
is exposed to the network. The added test goes through the view function, and
it does fail on that revert.

This also corrects an earlier claim of mine. I reported that GET /api/v3/config
did not expose these values; that path 404s, so the check proved nothing. The
real route is /config/main and it exposed all of them.
2026-08-20 05:09:12 -04:00
4 changed files with 186 additions and 148 deletions
+2 -46
View File
@@ -9,7 +9,7 @@ import time
import logging import logging
import threading import threading
from typing import Dict, Optional, Any, Callable from typing import Dict, Optional, Any, Callable
from dataclasses import dataclass, field, fields from dataclasses import dataclass, field
try: try:
import psutil import psutil
@@ -102,50 +102,6 @@ class PluginResourceMonitor:
"psutil not available - resource monitoring will be limited to execution time only" "psutil not available - resource monitoring will be limited to execution time only"
) )
def _metrics_from_cache(self, plugin_id: str, cached: Any) -> "ResourceMetrics":
"""Build metrics from a cached record, ignoring anything unrecognised.
ResourceMetrics(**cached) raises TypeError on a single unexpected key,
and that exception escapes into plugin_manager, which reports it as
"plugin <id> operation failed". Every plugin fails, and the plugin
system never finishes initialising.
Seen on a live rig: every plugin failing with
ResourceMetrics.__init__() got an unexpected keyword argument
'consecutive_failures'
which is a plugin_health field, not a metrics one. How a health-shaped
record came to sit under a plugin_metrics key on that machine is not
established -- a restored backup that mixed two machines' caches is the
likeliest explanation -- but the loader should not be brittle enough for
it to matter. plugin_health already repairs its records field by field
rather than trusting whatever is on disk; this does the same.
Unknown keys are dropped and named once, so a genuine schema change is
visible in the log instead of silently discarded.
"""
if not isinstance(cached, dict):
self.logger.warning(
"Ignoring cached metrics for %s: expected a mapping, got %s",
plugin_id, type(cached).__name__)
return ResourceMetrics()
known = {f.name for f in fields(ResourceMetrics)}
unknown = sorted(set(cached) - known)
if unknown:
self.logger.warning(
"Dropping unrecognised field(s) from cached metrics for %s: %s",
plugin_id, ", ".join(unknown))
usable = {k: v for k, v in cached.items() if k in known}
try:
return ResourceMetrics(**usable)
except (TypeError, ValueError) as e:
self.logger.warning(
"Cached metrics for %s unusable (%s); starting fresh",
plugin_id, e)
return ResourceMetrics()
def _get_metrics_key(self, plugin_id: str) -> str: def _get_metrics_key(self, plugin_id: str) -> str:
"""Get cache key for plugin metrics.""" """Get cache key for plugin metrics."""
return f"plugin_metrics:{plugin_id}" return f"plugin_metrics:{plugin_id}"
@@ -170,7 +126,7 @@ class PluginResourceMonitor:
cache_key, max_age=None, memory_ttl=0 if force_reload else None cache_key, max_age=None, memory_ttl=0 if force_reload else None
) )
if cached: if cached:
metrics = self._metrics_from_cache(plugin_id, cached) metrics = ResourceMetrics(**cached)
else: else:
metrics = ResourceMetrics() metrics = ResourceMetrics()
self._metrics[plugin_id] = metrics self._metrics[plugin_id] = metrics
+143
View File
@@ -0,0 +1,143 @@
"""GET /config/main must not hand out credentials.
The endpoint returned the raw config to anyone who could reach the port, and
this web interface has no authentication of any kind. Measured against a live
rig, an unauthenticated request returned:
github.api_token 40 chars
incoming-packages.ha_token 183 chars
jellyfin-now-playing.api_key 32 chars
ledmatrix-weather.api_key 32 chars
on-air.mqtt_password 8 chars
youtube.api_key 20 chars
youtube-stats.api_key 39 chars
A GitHub token and a Home Assistant long-lived token among them.
The x-secret masking the plugin config endpoints use does not apply here: this
endpoint never consults a schema, and core keys such as github.api_token have
no schema to carry the marker. Several of those fields *are* tagged x-secret in
their plugin's schema and were still returned in full, which is what makes the
schema route the wrong one to rely on for this endpoint.
Matching on field name is blunt. For a whole-config dump it is the right
default: anything named like a credential should not leave the process, and a
new plugin that adds a differently-shaped secret is covered without anyone
remembering to tag it.
"""
import pytest
from web_interface.blueprints.api_v3 import (
_looks_like_a_credential,
_redact_credentials,
)
@pytest.mark.parametrize("name", [
"password", "mqtt_password", "opensky_password", "passwd",
"api_key", "apikey", "API_KEY", "flightaware_api_key",
"token", "ha_token", "api_token", "access_token",
"secret", "client_secret", "spotify_client_secret",
"access_key", "private_key",
])
def test_credential_names_are_recognised(name):
assert _looks_like_a_credential(name)
@pytest.mark.parametrize("name", [
"timezone", "city", "brightness", "enabled", "update_interval",
"favorite_teams", "display_duration", "keyword",
])
def test_ordinary_names_are_left_alone(name):
assert not _looks_like_a_credential(name)
def test_the_measured_leak_is_closed():
"""The exact shape taken off the rig."""
config = {
"github": {"api_token": "ghp_" + "x" * 36},
"incoming-packages": {"ha_token": "y" * 183, "enabled": True},
"jellyfin-now-playing": {"api_key": "z" * 32},
"on-air": {"mqtt_password": "hunter22"},
"youtube": {"api_key": "k" * 20},
"timezone": "America/New_York",
}
out = _redact_credentials(config)
assert out["github"]["api_token"] == ""
assert out["incoming-packages"]["ha_token"] == ""
assert out["jellyfin-now-playing"]["api_key"] == ""
assert out["on-air"]["mqtt_password"] == ""
assert out["youtube"]["api_key"] == ""
# Everything else survives, or the config editor breaks.
assert out["timezone"] == "America/New_York"
assert out["incoming-packages"]["enabled"] is True
def test_nested_and_listed_credentials_are_reached():
config = {"a": {"b": {"c": {"password": "p"}}},
"feeds": [{"name": "x", "api_key": "k"}, {"name": "y"}]}
out = _redact_credentials(config)
assert out["a"]["b"]["c"]["password"] == ""
assert out["feeds"][0]["api_key"] == ""
assert out["feeds"][0]["name"] == "x"
def test_the_original_is_not_mutated():
"""The caller holds the live config; redaction must not edit it in place."""
config = {"github": {"api_token": "keepme"}}
_redact_credentials(config)
assert config["github"]["api_token"] == "keepme"
def test_a_credential_shaped_container_is_still_walked():
"""`secrets: {...}` is a section name, not a value to blank."""
config = {"secrets": {"api_key": "k", "note": "keep"}}
out = _redact_credentials(config)
assert out["secrets"]["api_key"] == ""
assert out["secrets"]["note"] == "keep"
def test_non_dict_input_passes_through():
assert _redact_credentials("plain") == "plain"
assert _redact_credentials(7) == 7
assert _redact_credentials(None) is None
def test_the_endpoint_itself_redacts():
"""Through the view function, not the helper.
The helper tests above all passed with the route still returning
`config` -- reverting the one line that calls the redactor changed
nothing, because nothing exercised the route. A property asserted on a
helper is not a property asserted on the endpoint, and it is the endpoint
that is exposed to the network.
"""
import json as _json
from unittest.mock import MagicMock
import flask
from web_interface.blueprints import api_v3 as mod
raw = {"github": {"api_token": "ghp_secret_value"},
"timezone": "America/New_York"}
manager = MagicMock()
manager.load_config.return_value = raw
previous = getattr(mod.api_v3, "config_manager", None)
mod.api_v3.config_manager = manager
app = flask.Flask(__name__)
try:
with app.test_request_context("/config/main"):
response = mod.get_main_config()
payload = response.get_json() if hasattr(response, "get_json") else _json.loads(response[0].data)
finally:
mod.api_v3.config_manager = previous
data = payload["data"]
assert data["github"]["api_token"] == "", (
"the endpoint returned the token; the redactor is not wired in")
assert data["timezone"] == "America/New_York"
# And the config the manager handed over is untouched.
assert raw["github"]["api_token"] == "ghp_secret_value"
-100
View File
@@ -1,100 +0,0 @@
"""A malformed metrics cache entry must not take every plugin down with it.
`ResourceMetrics(**cached)` raises TypeError on a single unexpected key, and
that exception escapes into plugin_manager, which reports it per plugin as
"plugin <id> operation failed". Every plugin fails and the plugin system never
finishes initialising -- the health endpoint reports
`plugin_system: not_initialized` while the display itself keeps running.
Seen on a live rig, once per plugin, continuously:
ERROR - src.plugin_system.plugin_manager - plugin geochron operation failed:
ResourceMetrics.__init__() got an unexpected keyword argument
'consecutive_failures'
`consecutive_failures` belongs to plugin_health, not to metrics. How a
health-shaped record came to sit under a plugin_metrics key on that machine is
not established -- a restored backup that mixed two machines' caches is the
likeliest explanation, and the same rig had one restored onto it -- but a
loader that turns one bad cache entry into a total outage is the part worth
fixing. plugin_health already repairs its own records field by field rather
than trusting what is on disk.
"""
import logging
from dataclasses import fields
from unittest.mock import MagicMock
import pytest
from src.plugin_system.resource_monitor import PluginResourceMonitor, ResourceMetrics
class _Cache:
def __init__(self, payload=None):
self.payload = payload
def get(self, key, max_age=None, memory_ttl=None, **kwargs):
return self.payload
def set(self, key, data, ttl=None, **kwargs):
pass
def _monitor(payload):
m = PluginResourceMonitor(cache_manager=_Cache(payload))
m.logger = logging.getLogger("test")
return m
#: What the rig actually had under the metrics key.
HEALTH_SHAPED = {
"consecutive_failures": 0, "circuit_state": "closed",
"circuit_opened_time": None, "half_open_start_time": None,
"last_error": None, "last_failure_time": None,
"last_success_time": 1_700_000_000.0, "total_failures": 0,
"total_successes": 42,
}
def test_a_health_record_under_the_metrics_key_does_not_raise():
"""The exact failure: it must degrade, not take the plugin system down."""
monitor = _monitor(HEALTH_SHAPED)
metrics = monitor.get_metrics(" plugin-a".strip())
assert isinstance(metrics, ResourceMetrics)
def test_recognised_fields_in_a_mixed_record_are_kept():
"""Dropping the record wholesale would lose real history unnecessarily."""
mixed = dict(HEALTH_SHAPED, call_count=7, memory_mb=12.5)
metrics = _monitor(mixed).get_metrics("plugin-b")
assert metrics.call_count == 7
assert metrics.memory_mb == 12.5
def test_a_clean_record_still_loads_unchanged():
clean = {f.name: 3 for f in fields(ResourceMetrics)}
metrics = _monitor(clean).get_metrics("plugin-c")
for name in (f.name for f in fields(ResourceMetrics)):
assert getattr(metrics, name) == 3
def test_unknown_fields_are_named_in_the_log(caplog):
"""Silently discarding them would hide a real schema change."""
with caplog.at_level(logging.WARNING):
_monitor(HEALTH_SHAPED).get_metrics("plugin-d")
# getMessage(), not .message: the latter is only populated once a handler
# formats the record, so the obvious spelling silently never matches.
assert any("consecutive_failures" in r.getMessage() for r in caplog.records), \
caplog.text
@pytest.mark.parametrize("payload", ["a string", 42, ["a", "list"]])
def test_a_non_mapping_cache_entry_does_not_raise(payload):
metrics = _monitor(payload).get_metrics("plugin-e")
assert isinstance(metrics, ResourceMetrics)
def test_values_of_the_wrong_type_do_not_raise():
"""A dataclass will accept these, but a later float() on them would not."""
metrics = _monitor({"call_count": "not a number"}).get_metrics("plugin-f")
assert isinstance(metrics, ResourceMetrics)
+41 -2
View File
@@ -262,15 +262,54 @@ def _stop_display_service():
result['status'] = status result['status'] = status
return result return result
#: Field names whose value is a credential. Matched by name because this
#: endpoint returns the whole config, core keys included, and core config has
#: no schema to carry x-secret markers.
_CREDENTIAL_NAME_PARTS = ("password", "passwd", "secret", "token", "api_key",
"apikey", "access_key", "private_key", "client_secret")
def _looks_like_a_credential(name: str) -> bool:
lowered = name.lower()
return any(part in lowered for part in _CREDENTIAL_NAME_PARTS)
def _redact_credentials(value):
"""A copy of `value` with credential-named fields blanked.
/config/main returned the raw config to anyone who could reach the port,
and this interface has no authentication. On one rig that meant a 40-char
GitHub token, a 183-char Home Assistant token and five API keys were
readable by anything on the LAN.
The x-secret masking used by the plugin config endpoints does not help
here: this endpoint never consults a schema, and core keys such as
github.api_token have no schema to mark. Matching on the field name is
blunt, but for a whole-config dump the right default is that anything
named like a credential does not leave the process.
Blanked rather than removed, and safe to blank: POST /config/main merges
into the loaded config and only writes the keys it was given, so a client
that round-trips this response cannot erase a secret it never saw.
"""
if isinstance(value, dict):
return {k: ("" if _looks_like_a_credential(k) and not isinstance(v, (dict, list))
else _redact_credentials(v))
for k, v in value.items()}
if isinstance(value, list):
return [_redact_credentials(item) for item in value]
return value
@api_v3.route('/config/main', methods=['GET']) @api_v3.route('/config/main', methods=['GET'])
def get_main_config(): def get_main_config():
"""Get main configuration""" """Get main configuration, with credentials redacted."""
try: try:
if not api_v3.config_manager: if not api_v3.config_manager:
return jsonify({'status': 'error', 'message': 'Config manager not initialized'}), 500 return jsonify({'status': 'error', 'message': 'Config manager not initialized'}), 500
config = api_v3.config_manager.load_config() config = api_v3.config_manager.load_config()
return jsonify({'status': 'success', 'data': config}) return jsonify({'status': 'success', 'data': _redact_credentials(config)})
except Exception as e: except Exception as e:
logger.error('Unhandled exception', exc_info=True) logger.error('Unhandled exception', exc_info=True)
return jsonify({'status': 'error', 'message': 'An error occurred; see logs for details', 'details': describe_exception(e)}), 500 return jsonify({'status': 'error', 'message': 'An error occurred; see logs for details', 'details': describe_exception(e)}), 500