Compare commits

..

1 Commits

Author SHA1 Message Date
MechaCat02
0a3877be51 chore: full hop-by-hop header strip and 60s timeout on /api/* proxy
The SvelteKit proxy was only stripping host + content-length; the rest
of RFC 7230 §6.1 (connection, keep-alive, proxy-authenticate,
proxy-authorization, te, trailer, transfer-encoding, upgrade) leaked
through to axum. Axum doesn't emit them so the impact is theoretical,
but the proxy should be RFC-conformant. Also adds an AbortController
with a configurable 60s timeout (BACKEND_PROXY_TIMEOUT_MS) so a
wedged backend can't hang the browser request indefinitely — failures
surface as the standard 502 upstream_unavailable envelope.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 20:07:39 +02:00
7 changed files with 141 additions and 122 deletions

View File

@@ -51,3 +51,8 @@ MAX_FILE_BYTES=20971520
# internal docker network. Override only if you're running the # internal docker network. Override only if you're running the
# frontend container against a backend somewhere else. # frontend container against a backend somewhere else.
BACKEND_URL=http://backend:8080 BACKEND_URL=http://backend:8080
# Per-request wall-clock cap for the /api/* reverse proxy (milliseconds).
# Default 300000 (5 min) covers a typical 200 MiB chapter upload over
# 25 Mbps; raise for users on slower upstream links or lower if a
# tighter front proxy already bounds the request lifetime.
BACKEND_PROXY_TIMEOUT_MS=300000

View File

@@ -1,6 +1,6 @@
[package] [package]
name = "mangalord" name = "mangalord"
version = "0.34.1" version = "0.34.0"
edition = "2021" edition = "2021"
default-run = "mangalord" default-run = "mangalord"

View File

@@ -4,8 +4,6 @@
//! expire naturally rather than being explicitly invalidated, so other //! expire naturally rather than being explicitly invalidated, so other
//! devices keep their existing logins). //! devices keep their existing logins).
use std::sync::OnceLock;
use axum::extract::{Path, State}; use axum::extract::{Path, State};
use axum::http::StatusCode; use axum::http::StatusCode;
use axum::response::IntoResponse; use axum::response::IntoResponse;
@@ -104,15 +102,9 @@ async fn login(
)); ));
} }
let user = repo::user::find_by_username(&state.db, username).await?; let user = repo::user::find_by_username(&state.db, username)
let Some(user) = user else { .await?
// No such user. Run argon2 against a stable dummy hash so the .ok_or(AppError::Unauthenticated)?;
// response time matches the wrong-password branch — otherwise
// an attacker can enumerate usernames by timing the no-user
// 401 against the wrong-password 401.
let _ = verify_password(&input.password, dummy_password_hash());
return Err(AppError::Unauthenticated);
};
if !verify_password(&input.password, &user.password_hash) { if !verify_password(&input.password, &user.password_hash) {
return Err(AppError::Unauthenticated); return Err(AppError::Unauthenticated);
} }
@@ -121,21 +113,6 @@ async fn login(
Ok((StatusCode::OK, jar, Json(AuthResponse { user }))) Ok((StatusCode::OK, jar, Json(AuthResponse { user })))
} }
/// Lazily-computed argon2 hash used to equalise login response time
/// across the "no such user" and "wrong password" branches. Computing
/// it once (on the first login of the process) is enough — the hash is
/// never compared against a real password, only used to force argon2
/// to do the same amount of work it would for a real verify.
fn dummy_password_hash() -> &'static str {
static DUMMY: OnceLock<String> = OnceLock::new();
DUMMY
.get_or_init(|| {
crate::auth::password::hash_password("login-timing-equaliser")
.expect("hash_password on a fixed input cannot fail")
})
.as_str()
}
async fn logout( async fn logout(
State(state): State<AppState>, State(state): State<AppState>,
jar: CookieJar, jar: CookieJar,

View File

@@ -567,91 +567,6 @@ async fn user_a_cannot_delete_user_b_token(pool: PgPool) {
assert_eq!(resp.status(), StatusCode::NO_CONTENT); assert_eq!(resp.status(), StatusCode::NO_CONTENT);
} }
/// Username enumeration via login response time: an attacker probes
/// for valid usernames by measuring how long /auth/login takes. Before
/// the equalisation fix, the no-user branch returned 401 in <1 ms
/// while the wrong-password branch took ~50-100 ms (the argon2 verify
/// cost). This test asserts the no-user branch now spends at least
/// some meaningful fraction of the wrong-password branch's time.
///
/// Tolerance is intentionally loose so CI variance doesn't flap the
/// test. The unequalised gap is large enough (~50x) that even a noisy
/// CI run with a 5x slack still catches it.
#[sqlx::test(migrations = "./migrations")]
async fn login_no_user_branch_runs_argon2_for_timing_equalisation(pool: PgPool) {
use std::time::Instant;
let h = common::harness(pool);
// Register the victim user so the wrong-password branch has a real
// argon2 hash to verify against.
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/register",
json!({ "username": "victim", "password": "hunter2hunter2" }),
))
.await
.unwrap();
// Warm-up: first login of the process initialises the dummy hash
// lazily. Skip that cost when measuring.
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/login",
json!({ "username": "victim", "password": "wrong" }),
))
.await
.unwrap();
let _ = h
.app
.clone()
.oneshot(common::post_json(
"/api/v1/auth/login",
json!({ "username": "ghost", "password": "wrong" }),
))
.await
.unwrap();
// Median-of-N is more stable than a single sample.
async fn sample_min(
app: &axum::Router,
username: &str,
n: u32,
) -> std::time::Duration {
let mut samples = Vec::with_capacity(n as usize);
for _ in 0..n {
let req = common::post_json(
"/api/v1/auth/login",
json!({ "username": username, "password": "wrong-guess" }),
);
let t = Instant::now();
let resp = app.clone().oneshot(req).await.unwrap();
let d = t.elapsed();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
samples.push(d);
}
// Use the minimum: it's the floor that argon2 takes, robust
// against unrelated stalls (DB connection acquisition, etc.).
*samples.iter().min().unwrap()
}
let wrong_pwd = sample_min(&h.app, "victim", 3).await;
let no_user = sample_min(&h.app, "ghost", 3).await;
// 5x slack: argon2 dominates both branches, so they should be
// within an order of magnitude. Unequalised, no_user would be
// ~50-100x faster. Asserting "no_user >= wrong_pwd / 5" catches
// the bug without being flaky in CI.
assert!(
no_user * 5 >= wrong_pwd,
"login timing leaks user existence: no_user={no_user:?}, wrong_pwd={wrong_pwd:?}"
);
}
#[sqlx::test(migrations = "./migrations")] #[sqlx::test(migrations = "./migrations")]
async fn delete_unknown_token_is_404(pool: PgPool) { async fn delete_unknown_token_is_404(pool: PgPool) {
let h = common::harness(pool); let h = common::harness(pool);

View File

@@ -1,6 +1,6 @@
{ {
"name": "mangalord-frontend", "name": "mangalord-frontend",
"version": "0.34.1", "version": "0.34.0",
"private": true, "private": true,
"type": "module", "type": "module",
"scripts": { "scripts": {

View File

@@ -118,4 +118,77 @@ describe('hooks.server proxy', () => {
expect(body.error.code).toBe('upstream_unavailable'); expect(body.error.code).toBe('upstream_unavailable');
expect(errSpy).toHaveBeenCalled(); expect(errSpy).toHaveBeenCalled();
}); });
it('strips every hop-by-hop header listed in RFC 7230 §6.1', async () => {
// Defence in depth: axum doesn't emit these, but a future
// middleware that did would otherwise leak per-connection
// state across the proxy boundary.
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
const resolve = vi.fn();
await handle({
event: makeEvent('/api/v1/health', {
headers: {
host: 'app.example.com',
'content-length': '0',
connection: 'keep-alive',
'keep-alive': 'timeout=5',
'proxy-authenticate': 'Basic realm=x',
'proxy-authorization': 'Basic xyz',
te: 'trailers',
trailer: 'Expires',
'transfer-encoding': 'chunked',
upgrade: 'websocket',
// A non-hop-by-hop header to ensure non-targets
// aren't accidentally stripped.
'x-custom': 'pass-through'
}
}),
resolve
});
const init = fetchSpy.mock.calls[0][1] as RequestInit;
const headers = init.headers as Headers;
for (const h of [
'host',
'content-length',
'connection',
'keep-alive',
'proxy-authenticate',
'proxy-authorization',
'te',
'trailer',
'transfer-encoding',
'upgrade'
]) {
expect(headers.get(h), `${h} should be stripped`).toBeNull();
}
expect(headers.get('x-custom')).toBe('pass-through');
});
it('aborts and returns 502 when the upstream stalls past the timeout', async () => {
const errSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
// Simulate an aborted fetch (AbortController.abort() raises a
// DOMException with name 'AbortError' on Node's fetch). The
// handler should treat it as the same upstream_unavailable
// 502 it uses for any other network failure.
const abortErr = new DOMException('aborted', 'AbortError');
fetchSpy.mockRejectedValueOnce(abortErr);
const resolve = vi.fn();
const resp = await handle({ event: makeEvent('/api/v1/slow'), resolve });
expect(resp.status).toBe(502);
const body = await resp.json();
expect(body.error.code).toBe('upstream_unavailable');
expect(errSpy).toHaveBeenCalled();
});
it('attaches an AbortSignal to the upstream fetch so it can time out', async () => {
fetchSpy.mockResolvedValueOnce(new Response('[]', { status: 200 }));
const resolve = vi.fn();
await handle({ event: makeEvent('/api/v1/health'), resolve });
const init = fetchSpy.mock.calls[0][1] as RequestInit;
expect(init.signal).toBeInstanceOf(AbortSignal);
// The signal hasn't fired (handler returned in time), but its
// presence is the contract this test is pinning.
expect(init.signal?.aborted).toBe(false);
});
}); });

View File

@@ -12,20 +12,66 @@ import type { Handle } from '@sveltejs/kit';
const BACKEND_URL = process.env.BACKEND_URL ?? 'http://localhost:8080'; const BACKEND_URL = process.env.BACKEND_URL ?? 'http://localhost:8080';
/**
* Hop-by-hop headers per RFC 7230 §6.1. These are scoped to a single
* transport-level connection and must not be forwarded by a proxy.
* Plus `host` and `content-length`: `host` would mislead the backend
* about its origin, and `content-length` is recomputed by the upstream
* fetch from the body stream.
*/
const HOP_BY_HOP_HEADERS = [
'host',
'content-length',
'connection',
'keep-alive',
'proxy-authenticate',
'proxy-authorization',
'te',
'trailer',
'transfer-encoding',
'upgrade'
];
/**
* Cap each proxied request at 5 minutes. The bound exists to surface
* a wedged backend (stuck on a slow DB query, deadlocked, etc.) as a
* 502 rather than letting the browser request hang indefinitely.
*
* The default leans toward the slow-upload end of the spectrum: at a
* 1 Mbps upstream, a 200 MiB chapter upload (the default
* `MAX_REQUEST_BYTES` cap) needs ~27 minutes; 300 s covers the more
* realistic 25 Mbps urban-broadband case (~64 s for the same upload)
* with comfortable headroom. Operators serving very slow clients
* should raise `BACKEND_PROXY_TIMEOUT_MS`; operators behind a
* tighter upstream proxy may want to lower it. A future improvement
* is an idle-based timeout (reset per chunk) instead of this
* wall-clock budget — that's a fair bit more code, deferred.
*/
const PROXY_TIMEOUT_MS = (() => {
const raw = process.env.BACKEND_PROXY_TIMEOUT_MS;
const n = raw ? Number(raw) : 300_000;
return Number.isFinite(n) && n > 0 ? n : 300_000;
})();
export const handle: Handle = async ({ event, resolve }) => { export const handle: Handle = async ({ event, resolve }) => {
if (event.url.pathname.startsWith('/api/')) { if (event.url.pathname.startsWith('/api/')) {
const target = `${BACKEND_URL}${event.url.pathname}${event.url.search}`; const target = `${BACKEND_URL}${event.url.pathname}${event.url.search}`;
// Strip hop-by-hop headers — `host` would mislead the backend
// about the origin, and `content-length` will be recomputed.
const headers = new Headers(event.request.headers); const headers = new Headers(event.request.headers);
headers.delete('host'); for (const h of HOP_BY_HOP_HEADERS) headers.delete(h);
headers.delete('content-length');
// AbortController times the upstream fetch out so a backend
// wedged on a slow DB query doesn't keep the browser request
// hanging forever. The `signal` is also wired into the
// RequestInit so the body stream is cancelled cleanly.
const ctrl = new AbortController();
const timeoutHandle = setTimeout(() => ctrl.abort(), PROXY_TIMEOUT_MS);
const init: RequestInit & { duplex?: 'half' } = { const init: RequestInit & { duplex?: 'half' } = {
method: event.request.method, method: event.request.method,
headers, headers,
redirect: 'manual' redirect: 'manual',
signal: ctrl.signal
}; };
if (event.request.method !== 'GET' && event.request.method !== 'HEAD') { if (event.request.method !== 'GET' && event.request.method !== 'HEAD') {
init.body = event.request.body; init.body = event.request.body;
@@ -39,11 +85,13 @@ export const handle: Handle = async ({ event, resolve }) => {
upstream = await fetch(target, init); upstream = await fetch(target, init);
} catch (e) { } catch (e) {
// Network-layer failure (DNS / connection refused / TLS // Network-layer failure (DNS / connection refused / TLS
// handshake) — most commonly "backend container restarting". // handshake / abort by timeout) — most commonly "backend
// SvelteKit's default 500 would be an HTML page that // container restarting". SvelteKit's default 500 would be
// client.ts can't .json(), which masks the real cause. Emit // an HTML page that client.ts can't .json(), which masks
// the standard envelope with a dedicated code instead. // the real cause. Emit the standard envelope with a
// dedicated code instead.
console.error('Proxy to backend failed:', e); console.error('Proxy to backend failed:', e);
clearTimeout(timeoutHandle);
return new Response( return new Response(
JSON.stringify({ JSON.stringify({
error: { error: {
@@ -58,6 +106,7 @@ export const handle: Handle = async ({ event, resolve }) => {
); );
} }
clearTimeout(timeoutHandle);
return new Response(upstream.body, { return new Response(upstream.body, {
status: upstream.status, status: upstream.status,
statusText: upstream.statusText, statusText: upstream.statusText,