fix(upload): server-side MIME/ext allowlist + atomic transactional write

C2: stored-XSS via the application/* MIME bypass is closed — the declared
Content-Type and client filename are no longer trusted. New classify() derives
both the canonical MIME and a safe extension purely from magic bytes against a
strict allowlist (jpeg/png/webp/heic/mp4/mov/webm); anything infer can't
positively identify (incl. HTML/SVG script payloads) is rejected. Unit tests
cover accept + reject paths.

M12: the stored extension can no longer carry '/' or arbitrary client text —
it's one of the allowlist's safe constants, ending directory-pollution and the
export DoS.

M5/M6: quota is now reserved with a single conditional UPDATE that row-locks
(no TOCTOU overshoot) and the reservation + row INSERT run in one transaction;
the file is written before commit and unlinked on any rollback, so a crash
mid-write can no longer leak quota bytes or orphan a row. Upload::create is now
executor-generic to run inside the tx.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/src/handlers/upload.rs

@@ -16,6 +16,35 @@ use crate::state::AppState;
 
 const MAX_CAPTION_LENGTH: usize = 2000;
 
+/// Derive the canonical MIME type and a *safe* file extension purely from the
+/// file's magic bytes, against a strict allowlist. The client-declared
+/// `Content-Type` and the client filename are never trusted: the old code
+/// skipped validation entirely for `application/*` and copied the extension
+/// verbatim from the filename, which allowed storing `{uuid}.html`/`.svg` with
+/// a script payload (stored XSS) and `/`-bearing extensions (path pollution +
+/// export DoS).
+///
+/// `infer` cannot fingerprint HTML/SVG, so the reject-by-default arm is exactly
+/// what closes the XSS vector — anything not positively identified as an allowed
+/// raster image or video is refused. Returns `(canonical_mime, safe_ext, is_video)`.
+fn classify(data: &[u8]) -> Result<(&'static str, &'static str, bool), AppError> {
+    let kind = infer::get(data)
+        .ok_or_else(|| AppError::BadRequest("Dateityp konnte nicht erkannt werden.".into()))?;
+    match kind.mime_type() {
+        "image/jpeg" => Ok(("image/jpeg", "jpg", false)),
+        "image/png" => Ok(("image/png", "png", false)),
+        "image/webp" => Ok(("image/webp", "webp", false)),
+        // infer reports HEIC/HEIF as image/heif
+        "image/heif" | "image/heic" => Ok(("image/heic", "heic", false)),
+        "video/mp4" => Ok(("video/mp4", "mp4", true)),
+        "video/quicktime" => Ok(("video/quicktime", "mov", true)),
+        "video/webm" => Ok(("video/webm", "webm", true)),
+        other => Err(AppError::BadRequest(format!(
+            "Dateityp nicht erlaubt: {other}. Erlaubt sind JPEG, PNG, WebP, HEIC, MP4, MOV, WebM."
+        ))),
+    }
+}
+
 pub async fn upload(
     State(state): State<AppState>,
     auth: AuthUser,
@@ -62,8 +91,6 @@ pub async fn upload(
     let max_video_mb: i64 = config::get_i64(&state.pool, "max_video_size_mb", 500).await;
 
     let mut file_data: Option<Vec<u8>> = None;
-    let mut file_name: Option<String> = None;
-    let mut content_type: Option<String> = None;
     let mut caption: Option<String> = None;
     let mut hashtags_csv: Option<String> = None;
 
@@ -71,8 +98,9 @@ pub async fn upload(
         let name = field.name().unwrap_or_default().to_string();
         match name.as_str() {
             "file" => {
-                file_name = field.file_name().map(|s| s.to_string());
+                // The client-declared filename and Content-Type are deliberately
-                content_type = field.content_type().map(|s| s.to_string());
+                // ignored — the stored MIME and extension are derived from the
+                // file's magic bytes (see `classify`).
                 file_data = Some(
                     field.bytes().await
                         .map_err(|e| AppError::BadRequest(format!("Datei konnte nicht gelesen werden: {e}")))?
@@ -96,7 +124,6 @@ pub async fn upload(
     }
 
     let data = file_data.ok_or_else(|| AppError::BadRequest("Keine Datei hochgeladen.".into()))?;
-    let mime = content_type.unwrap_or_else(|| "application/octet-stream".to_string());
     let size = data.len() as i64;
 
     // Validate caption length. Counted in chars (code points) to match the
@@ -111,25 +138,13 @@ pub async fn upload(
         }
     }
 
-    // Validate file MIME type using magic bytes
+    // Derive canonical MIME + safe extension from magic bytes against a strict
-    let detected_mime = infer::get(&data);
+    // allowlist. The client Content-Type and filename are never trusted.
-    if let Some(detected) = detected_mime {
+    let (canonical_mime, safe_ext, is_video) = classify(&data)?;
-        let detected_type = detected.mime_type();
+    let canonical_mime = canonical_mime.to_string();
-        // Ensure detected type is compatible with declared MIME type
-        let declared_category = mime.split('/').next().unwrap_or("");
-        let detected_category = detected_type.split('/').next().unwrap_or("");
 
-        // Only reject if categories don't match (e.g., image vs video)
+    // Validate file size against the per-category limit.
-        if declared_category != "application" && declared_category != detected_category {
+    let max_bytes = if is_video {
-            return Err(AppError::BadRequest(format!(
-                "Dateiinhalt entspricht nicht dem deklarierten Typ. Erwartet: {}, erkannt: {}",
-                mime, detected_type
-            )));
-        }
-    }
-
-    // Validate file size
-    let max_bytes = if mime.starts_with("video/") {
         max_video_mb * 1024 * 1024
     } else {
         max_image_mb * 1024 * 1024
@@ -141,59 +156,100 @@ pub async fn upload(
         )));
     }
 
-    // Per-user storage quota — dynamic formula based on available disk space and the
-    // number of active uploaders. Gated by master + per-area toggles so the admin can
-    // disable it on trusted instances.
-    let quota_on = config::get_bool(&state.pool, "quota_enabled", true).await;
-    let storage_quota_on = config::get_bool(&state.pool, "storage_quota_enabled", true).await;
-    if quota_on && storage_quota_on {
-        let estimate = compute_storage_quota(&state).await;
-        if let Some(limit) = estimate.limit_bytes {
-            let prospective_total = user.total_upload_bytes.saturating_add(size);
-            if prospective_total > limit {
-                return Err(AppError::TooManyRequests(
-                    "Du hast dein Upload-Limit für dieses Event erreicht.".into(),
-                    None,
-                ));
-            }
-        }
-    }
-
-    // Determine file extension
-    let ext = file_name
-        .as_deref()
-        .and_then(|n| n.rsplit('.').next())
-        .unwrap_or(if mime.starts_with("video/") { "mp4" } else { "jpg" });
-
     let upload_id = Uuid::new_v4();
     let event_slug = &state.config.event_slug;
-    let relative_path = format!("originals/{event_slug}/{upload_id}.{ext}");
+    let relative_path = format!("originals/{event_slug}/{upload_id}.{safe_ext}");
     let absolute_path = state.config.media_path.join(&relative_path);
 
-    // Ensure directory exists and write file
+    // Per-user storage quota — dynamic formula based on available disk space and the
-    if let Some(parent) = absolute_path.parent() {
+    // number of active uploaders. Gated by master + per-area toggles so the admin can
-        tokio::fs::create_dir_all(parent).await.map_err(|e| AppError::Internal(e.into()))?;
+    // disable it on trusted instances. `None` ⇒ enforcement off.
-    }
+    let quota_on = config::get_bool(&state.pool, "quota_enabled", true).await;
-    tokio::fs::write(&absolute_path, &data).await.map_err(|e| AppError::Internal(e.into()))?;
+    let storage_quota_on = config::get_bool(&state.pool, "storage_quota_enabled", true).await;
+    let quota_limit: Option<i64> = if quota_on && storage_quota_on {
+        compute_storage_quota(&state).await.limit_bytes
+    } else {
+        None
+    };
 
-    // Update user's total upload bytes
+    // Reserve quota and insert the row in a single transaction so the byte
-    sqlx::query("UPDATE \"user\" SET total_upload_bytes = total_upload_bytes + $2 WHERE id = $1")
+    // counter and the upload row are atomic (M6: no quota leak if we crash
+    // between them) and the reservation is a conditional UPDATE that row-locks
+    // (M5: concurrent uploads can no longer all pass a stale snapshot and
+    // overshoot the limit). The file is written before commit and unlinked on
+    // any rollback so a failed transaction leaves nothing behind.
+    let mut tx = state.pool.begin().await?;
+
+    let reserved: Option<(Uuid,)> = if let Some(limit) = quota_limit {
+        sqlx::query_as(
+            "UPDATE \"user\"
+             SET total_upload_bytes = total_upload_bytes + $2
+             WHERE id = $1 AND total_upload_bytes + $2 <= $3
+             RETURNING id",
+        )
         .bind(auth.user_id)
         .bind(size)
-        .execute(&state.pool)
+        .bind(limit)
-        .await?;
+        .fetch_optional(&mut *tx)
+        .await?
+    } else {
+        sqlx::query_as(
+            "UPDATE \"user\"
+             SET total_upload_bytes = total_upload_bytes + $2
+             WHERE id = $1
+             RETURNING id",
+        )
+        .bind(auth.user_id)
+        .bind(size)
+        .fetch_optional(&mut *tx)
+        .await?
+    };
+    if reserved.is_none() {
+        // The user exists (checked above), so a missing row here means the
+        // conditional limit guard rejected the reservation → over quota.
+        tx.rollback().await.ok();
+        return Err(AppError::TooManyRequests(
+            "Du hast dein Upload-Limit für dieses Event erreicht.".into(),
+            None,
+        ));
+    }
 
-    // Insert upload record
+    // Write the file. On any failure, roll back (releasing the reservation) and
-    let upload = Upload::create(
+    // remove a possibly-partial file.
-        &state.pool,
+    if let Some(parent) = absolute_path.parent() {
+        if let Err(e) = tokio::fs::create_dir_all(parent).await {
+            tx.rollback().await.ok();
+            return Err(AppError::Internal(e.into()));
+        }
+    }
+    if let Err(e) = tokio::fs::write(&absolute_path, &data).await {
+        tx.rollback().await.ok();
+        return Err(AppError::Internal(e.into()));
+    }
+
+    let upload = match Upload::create(
+        &mut *tx,
         auth.event_id,
         auth.user_id,
         &relative_path,
-        &mime,
+        &canonical_mime,
         size,
         caption.as_deref(),
     )
-    .await?;
+    .await
+    {
+        Ok(u) => u,
+        Err(e) => {
+            tx.rollback().await.ok();
+            let _ = tokio::fs::remove_file(&absolute_path).await;
+            return Err(e.into());
+        }
+    };
+
+    if let Err(e) = tx.commit().await {
+        let _ = tokio::fs::remove_file(&absolute_path).await;
+        return Err(e.into());
+    }
 
     // Process hashtags from caption and explicit CSV
     let mut tags: Vec<String> = Vec::new();
@@ -219,7 +275,7 @@ pub async fn upload(
     // Spawn compression task
     state
         .compression
-        .process(upload.id, relative_path, mime.clone());
+        .process(upload.id, relative_path, canonical_mime.clone());
 
     // Broadcast SSE event
     let dto = UploadDto {
@@ -228,7 +284,7 @@ pub async fn upload(
         uploader_name: user.display_name,
         preview_url: None,
         thumbnail_url: None,
-        mime_type: mime,
+        mime_type: canonical_mime,
         caption,
         hashtags: tags,
         like_count: 0,
@@ -411,3 +467,41 @@ pub async fn get_original(
         .body(Body::from_stream(stream))
         .map_err(|e| AppError::Internal(e.into()))
 }
+
+#[cfg(test)]
+mod tests {
+    use super::classify;
+
+    #[test]
+    fn classify_accepts_allowed_image_types() {
+        // PNG signature
+        let png = [0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A, 0, 0, 0, 0];
+        let (mime, ext, is_video) = classify(&png).expect("png allowed");
+        assert_eq!(mime, "image/png");
+        assert_eq!(ext, "png");
+        assert!(!is_video);
+
+        // JPEG signature
+        let jpeg = [0xFF, 0xD8, 0xFF, 0xE0, 0, 0, 0, 0, 0, 0, 0, 0];
+        let (mime, ext, _) = classify(&jpeg).expect("jpeg allowed");
+        assert_eq!(mime, "image/jpeg");
+        assert_eq!(ext, "jpg");
+    }
+
+    #[test]
+    fn classify_rejects_unrecognized_and_html_svg() {
+        // Plain HTML / script payload — infer cannot fingerprint it, so it must
+        // be rejected (this is the stored-XSS vector the old code let through
+        // via a declared `application/*` Content-Type).
+        let html = b"<html><script>alert(1)</script></html>";
+        assert!(classify(html).is_err());
+
+        // SVG (text-based) is likewise unrecognized → rejected.
+        let svg = b"<svg xmlns=\"http://www.w3.org/2000/svg\"><script>x</script></svg>";
+        assert!(classify(svg).is_err());
+
+        // Empty / garbage.
+        assert!(classify(&[]).is_err());
+        assert!(classify(&[0x00, 0x01, 0x02, 0x03]).is_err());
+    }
+}

backend/src/models/upload.rs

@@ -36,15 +36,21 @@ pub struct UploadDto {
 }
 
 impl Upload {
-    pub async fn create(
+    /// Generic over the executor so it can run inside the upload transaction
-        pool: &PgPool,
+    /// (`&mut *tx`) alongside the quota-counter reservation, keeping the
+    /// byte-counter and the row atomic (no quota leak on a mid-write crash).
+    pub async fn create<'e, E>(
+        executor: E,
         event_id: Uuid,
         user_id: Uuid,
         original_path: &str,
         mime_type: &str,
         original_size_bytes: i64,
         caption: Option<&str>,
-    ) -> Result<Self, sqlx::Error> {
+    ) -> Result<Self, sqlx::Error>
+    where
+        E: sqlx::PgExecutor<'e>,
+    {
         sqlx::query_as::<_, Self>(
             "INSERT INTO upload (event_id, user_id, original_path, mime_type, original_size_bytes, caption)
              VALUES ($1, $2, $3, $4, $5, $6)
@@ -56,7 +62,7 @@ impl Upload {
         .bind(mime_type)
         .bind(original_size_bytes)
         .bind(caption)
-        .fetch_one(pool)
+        .fetch_one(executor)
         .await
     }