1
0
mirror of https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git synced 2026-11-03 01:13:24 +00:00

fix(gateway)!: replace token cookies with revocable sessions and harden abuse controls (#40)

- Replace user:token cookies with opaque server-side sessions, revocable on logout, delete, recreate and expiry; bind every credential to the path user and add cross-user regression tests.
- Rate-limit /users and /login, add optional signup invite codes and form same-origin checks, and unify login failures to 401.
- Require explicit ALLOW_INSECURE_COOKIES for plain HTTP, use __Host-dsh_gw_session when secure, and fix secure cookie deletion.
- Strip client-supplied forwarding/SSO headers, add an optional upstream allowlist, per-user in-flight and WebSocket message caps, credential-free handshake errors, and sweep-time state pruning.
- Digest-pin base images, hash-pin gateway dependencies, verify DSH_COMMIT in the build, and run the gateway image as non-root with a pinned Python base.
- Update manifests, production checklist, architecture/security docs and add an SSO preflight script.

BREAKING CHANGE: existing dsh_gw_session=<user>:<token> cookies are invalid; users must sign in again. Unknown users on POST /login now return 401 instead of 404, and the gateway refuses COOKIE_SECURE=false unless ALLOW_INSECURE_COOKIES=1.

Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
This commit is contained in:
SREDevOps.org Agent
2026-10-31 00:57:35 -03:00
committed by GitHub
parent 2f959e6afb
commit 1a929e3e24
33 changed files with 5450 additions and 319 deletions

View File

@@ -0,0 +1,234 @@
#!/usr/bin/env bash
# Preflight for the gateway-api-sso exposure variant.
#
# Run this AFTER creating the oauth2-proxy/TLS Secrets, setting the gateway
# env and applying manifests/exposure/gateway-api-sso/, and BEFORE sending real
# traffic. It checks the configuration that is easy to get wrong and whose
# failure is either silent (login appears to work but the gateway still asks
# for its own token) or dangerous (a spoofable identity header, a placeholder
# host, a TLS Secret that does not exist).
#
# Checks:
# 1. kubectl reaches the cluster and the SSO objects exist;
# 2. the oauth2-proxy Secret has client-id, client-secret and a cookie-secret
# that decodes to 16, 24 or 32 bytes; the TLS Secret exists;
# 3. deploy/dsh-gateway has AUTH_PROXY_HEADER=X-Forwarded-User and
# COOKIE_SECURE=true (both are opt-in and both are required for SSO over
# TLS);
# 4. the Gateway's TLS certificate reference resolves to an existing Secret;
# 5. no your-github-org / dsh-demo.example.com placeholder is left in the
# applied oauth2-proxy args, Gateway listeners or HTTPRoute hostnames;
# 6. (warning) no Ingress in the namespace creates a second path to
# dsh-gateway. With SSO enabled the Service must be reachable only through
# oauth2-proxy.
#
# Exit status: 0 when every check passes (warnings allowed), 1 on any failure.
# Every failure prints the fix. This script only reads cluster state.
#
# Usage:
# examples/dsh-agents-as-a-service/scripts/preflight-sso.sh
#
# Environment overrides:
# NAMESPACE namespace (default: dsh-demo)
# GATEWAY_DEPLOY gateway Deployment name (default: dsh-gateway)
# OAUTH_DEPLOY oauth2-proxy Deployment name (default: oauth2-proxy)
# OAUTH_SECRET oauth2-proxy Secret name (default: oauth2-proxy)
# TLS_SECRET TLS Secret name the Gateway should reference (default:
# dsh-demo-tls)
set -euo pipefail
cd "$(dirname "$0")/.."
NS="${NAMESPACE:-dsh-demo}"
GATEWAY_DEPLOY="${GATEWAY_DEPLOY:-dsh-gateway}"
OAUTH_DEPLOY="${OAUTH_DEPLOY:-oauth2-proxy}"
OAUTH_SECRET="${OAUTH_SECRET:-oauth2-proxy}"
TLS_SECRET="${TLS_SECRET:-dsh-demo-tls}"
FAILED=0
pass() { printf 'PASS %s\n' "$*"; }
warn() { printf 'WARN %s\n' "$*" >&2; }
fail() { printf 'FAIL %s\n' "$*" >&2; FAILED=1; }
if ! command -v kubectl >/dev/null 2>&1; then
echo "FAIL kubectl is not installed; install it and select the target context" >&2
exit 1
fi
if ! kubectl -n "$NS" get deployment "$GATEWAY_DEPLOY" >/dev/null 2>&1; then
echo "FAIL deploy/$GATEWAY_DEPLOY not found in namespace $NS." >&2
echo " Apply the base manifests first: kubectl apply -f manifests/" >&2
echo " Then apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/" >&2
exit 1
fi
echo "== Secrets"
# check_secret_key <secret> <key> <hint>
check_secret_key() {
local secret=$1 key=$2 hint=$3 value escaped
# Kubernetes JSONPath treats "." as a path separator; escape it in keys such
# as tls.crt.
escaped=${key//./\\.}
value=$(kubectl -n "$NS" get secret "$secret" -o jsonpath="{.data.${escaped}}" 2>/dev/null || true)
if [ -n "$value" ]; then
pass "Secret $secret has non-empty key '$key'"
else
fail "Secret $secret is missing a non-empty '$key' key. $hint"
fi
}
check_secret_key "$OAUTH_SECRET" client-id \
"Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
check_secret_key "$OAUTH_SECRET" client-secret \
"Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
check_secret_key "$OAUTH_SECRET" cookie-secret \
"Create it from manifests/exposure/gateway-api-sso/73-oauth2-proxy-secret.yaml.example."
# The cookie secret must be URL-safe unpadded base64 of 16, 24 or 32 bytes;
# oauth2-proxy refuses anything else (the classic error is "44 bytes").
if COOKIE_B64=$(kubectl -n "$NS" get secret "$OAUTH_SECRET" \
-o jsonpath='{.data.cookie-secret}' 2>/dev/null); then
if [ -n "$COOKIE_B64" ]; then
if ! COOKIE_LEN=$(printf '%s' "$COOKIE_B64" | base64 -d 2>/dev/null | wc -c); then
fail "Secret $OAUTH_SECRET key 'cookie-secret' is not valid base64. Generate it with: python3 -c 'import secrets; print(secrets.token_urlsafe(32))'"
else
case "$COOKIE_LEN" in
16 | 24 | 32) pass "oauth2-proxy cookie-secret decodes to $COOKIE_LEN bytes" ;;
*)
fail "oauth2-proxy cookie-secret decodes to $COOKIE_LEN bytes; it must be 16, 24 or 32. Generate a URL-safe unpadded value with: python3 -c 'import secrets; print(secrets.token_urlsafe(32))'"
;;
esac
fi
fi
fi
check_secret_key "$TLS_SECRET" tls.crt \
"Create the TLS Secret with: kubectl -n $NS create secret tls $TLS_SECRET --cert=tls.crt --key=tls.key"
check_secret_key "$TLS_SECRET" tls.key \
"Create the TLS Secret with: kubectl -n $NS create secret tls $TLS_SECRET --cert=tls.crt --key=tls.key"
echo
echo "== Gateway SSO configuration (deploy/$GATEWAY_DEPLOY)"
GATEWAY_ENV=$(kubectl -n "$NS" get deployment "$GATEWAY_DEPLOY" \
-o jsonpath='{range .spec.template.spec.containers[*].env[*]}{.name}={.value}{"\n"}{end}')
# env_value <NAME>: print the literal env value, or nothing when unset.
env_value() {
printf '%s\n' "$GATEWAY_ENV" | awk -F= -v key="$1" '$1 == key { sub(/^[^=]*=/, ""); print }'
}
env_is_set() {
printf '%s\n' "$GATEWAY_ENV" | awk -F= -v key="$1" '$1 == key { found = 1 } END { exit found ? 0 : 1 }'
}
if ! env_is_set AUTH_PROXY_HEADER; then
fail "AUTH_PROXY_HEADER is not set on deploy/$GATEWAY_DEPLOY, so the gateway ignores oauth2-proxy's identity header and users are still asked for the gateway token. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY AUTH_PROXY_HEADER=X-Forwarded-User"
elif [ "$(env_value AUTH_PROXY_HEADER)" != "X-Forwarded-User" ]; then
fail "AUTH_PROXY_HEADER is '$(env_value AUTH_PROXY_HEADER)', expected 'X-Forwarded-User'. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY AUTH_PROXY_HEADER=X-Forwarded-User"
else
pass "AUTH_PROXY_HEADER=X-Forwarded-User"
fi
if ! env_is_set COOKIE_SECURE; then
fail "COOKIE_SECURE is not set on deploy/$GATEWAY_DEPLOY; the session cookie must be Secure behind TLS. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY COOKIE_SECURE=true"
elif [ "$(env_value COOKIE_SECURE | tr '[:upper:]' '[:lower:]')" != "true" ]; then
fail "COOKIE_SECURE is '$(env_value COOKIE_SECURE)', expected 'true' behind TLS. Fix: kubectl -n $NS set env deploy/$GATEWAY_DEPLOY COOKIE_SECURE=true"
else
pass "COOKIE_SECURE=true"
fi
if env_is_set ALLOW_INSECURE_COOKIES; then
warn "ALLOW_INSECURE_COOKIES is still set on deploy/$GATEWAY_DEPLOY. It is ignored while COOKIE_SECURE=true but is a footgun: remove it with 'kubectl -n $NS set env deploy/$GATEWAY_DEPLOY ALLOW_INSECURE_COOKIES-'."
fi
echo
echo "== SSO objects and placeholders"
if kubectl -n "$NS" get deployment "$OAUTH_DEPLOY" >/dev/null 2>&1; then
pass "deploy/$OAUTH_DEPLOY exists"
OAUTH_ARGS=$(kubectl -n "$NS" get deployment "$OAUTH_DEPLOY" \
-o jsonpath='{range .spec.template.spec.containers[*].args[*]}{@}{"\n"}{end}')
else
OAUTH_ARGS=""
fail "deploy/$OAUTH_DEPLOY not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
fi
# GitHub org restriction is the only authorization in the shipped variant.
# --email-domain=* is acceptable only because --github-org narrows membership;
# a missing or empty org value would accept any GitHub account.
if [ -n "$OAUTH_ARGS" ]; then
if printf '%s\n' "$OAUTH_ARGS" | grep -q '^--provider=github$'; then
pass "oauth2-proxy uses --provider=github"
else
fail "oauth2-proxy is not configured with --provider=github. Fix: add --provider=github to deploy/$OAUTH_DEPLOY."
fi
if printf '%s\n' "$OAUTH_ARGS" | grep -Eq '^--github-org=.+$'; then
pass "oauth2-proxy restricts membership with --github-org"
else
fail "oauth2-proxy has no non-empty --github-org. Fix: set --github-org=<your-org> in deploy/$OAUTH_DEPLOY; otherwise --email-domain=* accepts any GitHub account."
fi
fi
if kubectl -n "$NS" get httproute dsh-gateway >/dev/null 2>&1; then
pass "HTTPRoute dsh-gateway exists"
ROUTE_STATE=$(kubectl -n "$NS" get httproute dsh-gateway \
-o jsonpath='{.spec.hostnames[*]}' 2>/dev/null || true)
else
ROUTE_STATE=""
fail "HTTPRoute dsh-gateway not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
fi
if kubectl -n "$NS" get gateway dsh-gateway >/dev/null 2>&1; then
pass "Gateway dsh-gateway exists"
GATEWAY_STATE=$(kubectl -n "$NS" get gateway dsh-gateway \
-o jsonpath='{range .spec.listeners[*]}{.hostname}{"\n"}{end}' 2>/dev/null || true)
CERT_REFS=$(kubectl -n "$NS" get gateway dsh-gateway \
-o jsonpath='{range .spec.listeners[*].tls.certificateRefs[*]}{.namespace}{"/"}{.name}{"\n"}{end}' 2>/dev/null || true)
else
GATEWAY_STATE=""
CERT_REFS=""
fail "Gateway dsh-gateway not found. Apply the variant: kubectl apply -f manifests/exposure/gateway-api-sso/"
fi
# Placeholders are the default values in the committed manifests. They reach
# the cluster if the variant is applied before editing them.
PLACEHOLDER_RE='your-github-org|dsh-demo\.example\.com'
PLACEHOLDER_STATE=$(printf '%s\n%s\n%s\n' "$OAUTH_ARGS" "$ROUTE_STATE" "$GATEWAY_STATE")
if printf '%s\n' "$PLACEHOLDER_STATE" | grep -En "$PLACEHOLDER_RE" >/dev/null 2>&1; then
fail "the applied SSO objects still contain a placeholder (your-github-org or dsh-demo.example.com):"
printf '%s\n' "$PLACEHOLDER_STATE" | grep -En "$PLACEHOLDER_RE" | sed 's/^/ /' >&2
echo " Replace --github-org, --redirect-url, the Gateway listener host and the HTTPRoute hostname with the real public FQDN and organization, then re-apply and restart the proxy." >&2
else
pass "no your-github-org / dsh-demo.example.com placeholder in the applied SSO objects"
fi
# The Gateway must reference an existing TLS Secret; the default name is
# dsh-demo-tls, but 70-gateway.yaml can be edited to another name.
if [ -n "$CERT_REFS" ]; then
while IFS= read -r ref; do
[ -n "$ref" ] || continue
ref_ns=${ref%%/*}
ref_name=${ref#*/}
ref_ns=${ref_ns:-$NS}
if kubectl -n "$ref_ns" get secret "$ref_name" >/dev/null 2>&1; then
pass "Gateway TLS certificate reference ${ref_ns}/${ref_name} exists"
else
fail "Gateway references TLS Secret ${ref_ns}/${ref_name} but it does not exist. Create it (see manifests/exposure/gateway-api-sso/74-tls-secret.yaml.example)."
fi
done <<<"$CERT_REFS"
else
warn "the Gateway has no TLS certificateRefs; SSO over plain HTTP would expose the session cookie. Terminate TLS at the Gateway listener."
fi
# A second path to the gateway defeats SSO: anyone who can reach
# dsh-gateway:8080 can spoof X-Forwarded-User. This is a best-effort check.
if kubectl -n "$NS" get ingress >/dev/null 2>&1; then
INGRESS_STATE=$(kubectl -n "$NS" get ingress -o json 2>/dev/null || true)
if printf '%s' "$INGRESS_STATE" | grep -q '"name":"dsh-gateway"'; then
fail "an Ingress in namespace $NS also routes to dsh-gateway. With SSO enabled the gateway must be reachable only through oauth2-proxy: delete the Ingress variant (kubectl delete -f manifests/exposure/ingress/)."
fi
fi
echo
if [ "$FAILED" -ne 0 ]; then
echo "preflight-sso: FAILED - fix the items above before exposing the gateway." >&2
exit 1
fi
echo "preflight-sso: ok - the SSO variant looks correctly configured."