feat(gateway): temporary IP ban (fail2ban) fed by rejections + honeypot/honeytoken
CI / changes (pull_request) Successful in 3s
CI / unit (pull_request) Successful in 11s
CI / integration (pull_request) Successful in 17s
CI / ui (pull_request) Successful in 53s
CI / gate (pull_request) Successful in 0s
CI / deploy (pull_request) Successful in 1m11s
CI / changes (pull_request) Successful in 3s
CI / unit (pull_request) Successful in 11s
CI / integration (pull_request) Successful in 17s
CI / ui (pull_request) Successful in 53s
CI / gate (pull_request) Successful in 0s
CI / deploy (pull_request) Successful in 1m11s
Add a prod-only, in-memory IP ban enforced at the edge, fed by three signals:
sustained rate-limiter rejections (the IP-keyed public/email/admin classes — the
user class stays the backend soft-flag's concern), a honeypot decoy-path hit (the
contour caddy tags decoys with X-Scrabble-Honeypot and routes them to the gateway),
and a honeytoken (a planted bearer, GATEWAY_HONEYTOKEN). A banned IP is refused with
429 by the abuseGuard middleware before any work — covering the Connect edge, the
live stream and the static SPA/landing the per-op limiter never gated.
The ban is off by default: it keys by the real client IP the shared-NAT test contour
does not expose, so a ban there would be self-inflicted; detection still logs in the
contour, only the ban action is gated (GATEWAY_ABUSE_BAN_ENABLED). Rejection bans last
GATEWAY_ABUSE_BAN_DURATION; tripwire/honeytoken hits are near-zero-false-positive and
earn longer fixed bans. Each ban increments gateway_abuse_banned_total{reason}.
Operators see and lift active bans on the admin console's Throttled page; the gateway
syncs its active set to the backend every 30s (POST /api/v1/internal/bans/sync,
backend/internal/banview) and applies the operator unbans the response returns.
PRERELEASE phase AG. Docs baked into ARCHITECTURE / FUNCTIONAL (+ru) / both READMEs.
This commit is contained in:
@@ -2,6 +2,7 @@ package config
|
||||
|
||||
import (
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
pkgtel "scrabble/pkg/telemetry"
|
||||
)
|
||||
@@ -45,3 +46,52 @@ func TestLoadMaxBodyBytes(t *testing.T) {
|
||||
t.Fatal("Load: expected an error for a non-positive body cap, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
// TestLoadAbuseDefaults verifies the anti-abuse ban defaults: disabled (prod-only),
|
||||
// the agreed thresholds, and no honeytoken.
|
||||
func TestLoadAbuseDefaults(t *testing.T) {
|
||||
c, err := Load()
|
||||
if err != nil {
|
||||
t.Fatalf("Load: %v", err)
|
||||
}
|
||||
want := DefaultAbuse()
|
||||
if c.Abuse != want {
|
||||
t.Errorf("Abuse = %+v, want %+v", c.Abuse, want)
|
||||
}
|
||||
if c.Abuse.BanEnabled {
|
||||
t.Error("ban must default to disabled (enabled only in prod)")
|
||||
}
|
||||
}
|
||||
|
||||
// TestLoadAbuseOverrides verifies the anti-abuse environment variables are parsed.
|
||||
func TestLoadAbuseOverrides(t *testing.T) {
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_ENABLED", "true")
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_THRESHOLD", "50")
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_WINDOW", "90s")
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_DURATION", "30m")
|
||||
t.Setenv("GATEWAY_HONEYTOKEN", "deadbeef")
|
||||
c, err := Load()
|
||||
if err != nil {
|
||||
t.Fatalf("Load: %v", err)
|
||||
}
|
||||
want := AbuseConfig{
|
||||
BanEnabled: true,
|
||||
BanThreshold: 50,
|
||||
BanWindow: 90 * time.Second,
|
||||
BanDuration: 30 * time.Minute,
|
||||
Honeytoken: "deadbeef",
|
||||
}
|
||||
if c.Abuse != want {
|
||||
t.Errorf("Abuse = %+v, want %+v", c.Abuse, want)
|
||||
}
|
||||
}
|
||||
|
||||
// TestLoadAbuseRejectsBadThreshold verifies an enabled ban with a non-positive
|
||||
// threshold fails validation.
|
||||
func TestLoadAbuseRejectsBadThreshold(t *testing.T) {
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_ENABLED", "true")
|
||||
t.Setenv("GATEWAY_ABUSE_BAN_THRESHOLD", "0")
|
||||
if _, err := Load(); err == nil {
|
||||
t.Fatal("Load: expected an error for an enabled ban with a zero threshold, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user