Fix DoS via sample-rate forgery bypassing audio decode duration guard (#49948)

Signed-off-by: jperezde <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Juan Pérez de Algaba
2026-08-10 15:49:17 +00:00
committed by GitHub
co-authored by Cursor
parent 37fbf52084
commit 640a09086d
5 changed files with 126 additions and 7 deletions
+1
View File
@@ -95,6 +95,7 @@ enforces decode-size limits to prevent out-of-memory denial of service:
| `VLLM_MAX_IMAGE_PIXELS` | `178956970` (~179M pixels) | Maximum decoded image size in pixels. Images exceeding this are rejected before raster memory is allocated. Default matches PIL's built-in 2x decompression-bomb threshold (~680 MB for RGB). |
| `VLLM_MAX_AUDIO_CLIP_FILESIZE_MB` | `25` | Maximum filesize in MB for a single audio file. |
| `VLLM_MAX_AUDIO_DECODE_DURATION_S` | `600` | Maximum decoded audio duration in seconds. Prevents compressed audio from expanding into gigabytes of float32 PCM. |
| `VLLM_MAX_AUDIO_DECODE_BYTES` | `268435456` (256 MiB) | Maximum float32 PCM bytes that audio decoding may allocate. Guards against sample-rate forgery where an inflated header sample rate bypasses the duration guard while the actual frame count causes a multi-GiB allocation. |
Setting any of these to `0` disables the corresponding limit. This is **not
recommended** for deployments exposed to untrusted users, as it removes the