Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI

GHSA-pq5c-rjhq-qp7p

MEDIUMFix: vllm-project/vllm#38636

GHSA-pq5c-rjhq-qp7p is a medium-severity (CVSS 6.5) CWE-770 vulnerability in vllm. O3 Security confirms whether GHSA-pq5c-rjhq-qp7p is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing

Also known asCVE-2026-34755PYSEC-2026-144
Published
Apr 3, 2026
Updated
Jul 17, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Summary

The VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py:51-62 splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path at line 47-48, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM.

Details

Vulnerable code

# video.py:51-62
def load_base64(self, media_type: str, data: str) -> tuple[npt.NDArray, dict[str, Any]]:
    if media_type.lower() == "video/jpeg":
        load_frame = partial(self.image_io.load_base64, "image/jpeg")
        return np.stack(
            [np.asarray(load_frame(frame_data)) for frame_data in data.split(",")]
            #                                                       ^^^^^^^^^^
            # Unbounded split — no frame count limit
        ), {}
    return self.load_bytes(base64.b64decode(data))

The load_bytes() path (line 47-48) properly delegates to a video loader that respects self.num_frames (default 32). The load_base64("video/jpeg", ...) path bypasses this limit entirely — data.split(",") produces an unbounded list and every frame is decoded into a numpy array.

video/jpeg is part of vLLM's public API

video/jpeg is a vLLM-specific MIME type, not IANA-registered. However it is part of the public API surface:

  • encode_video_url() at vllm/multimodal/utils.py:96-108 generates data:video/jpeg;base64,... URLs
  • Official test suites at tests/entrypoints/openai/test_video.py:62 and tests/entrypoints/test_chat_utils.py:153 both use this format

Memory amplification

Each JPEG frame decodes to a full numpy array. For 640x480 RGB images, each frame is ~921 KB decoded. 5000 frames = ~4.6 GB. np.stack() then creates an additional copy. The compressed JPEG payload is small (~100 KB for 5000 frames) but decompresses to gigabytes.

Data flow

POST /v1/chat/completions
  → chat_utils.py:1434   video_url type → mm_parser.parse_video()
  → chat_utils.py:872    parse_video() → self._connector.fetch_video()
  → connector.py:295     fetch_video() → load_from_url(url, self.video_io)
  → connector.py:91      _load_data_url(): url_spec.path.split(",", 1)
                          → media_type = "video/jpeg"
                          → data = "<frame1>,<frame2>,...,<frame10000>"
  → connector.py:100     media_io.load_base64("video/jpeg", data)
  → video.py:54          data.split(",")  ← UNBOUNDED
  → video.py:55-57       all frames decoded into numpy arrays
  → video.py:56          np.stack([...])  ← massive combined array → OOM

connector.py:91 uses split(",", 1) which splits on only the first comma. All remaining commas stay in data and are later split by video.py:54.

Comparison with existing protections

Code PathFrame LimitFile
load_bytes() (binary video)Yes — num_frames (default 32)video.py:46-49
load_base64("video/jpeg", ...)No — unlimited data.split(",")video.py:51-62

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm0.7.0&&< 0.19.00.19.0

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update vllm to 0.19.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-pq5c-rjhq-qp7p is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether GHSA-pq5c-rjhq-qp7p is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-pq5c-rjhq-qp7p. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

## Summary The `VideoMediaIO.load_base64()` method at `vllm/multimodal/media/video.py:51-62` splits `video/jpeg` data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The `num_frames` parameter (default: 32), which is enforced by the `load_bytes()` code path at line 47-48, is completely bypassed in the `video/jpeg` base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. ## Details ### Vulnerable code ```python #
O3 Security · Impact-Aware SCA

Is GHSA-pq5c-rjhq-qp7p in your dependencies?

O3 detects GHSA-pq5c-rjhq-qp7p across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.