How severe is GHSA-grg2-63fw-f2qr?

GHSA-grg2-63fw-f2qr has a CVSS score of 6.5/10, rated MEDIUM. Review your exposure and patch according to your risk tolerance.

Which packages are affected by GHSA-grg2-63fw-f2qr?

GHSA-grg2-63fw-f2qr affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-grg2-63fw-f2qr?

Update vllm to 0.12.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-grg2-63fw-f2qr is resolved across your whole dependency graph.

How do I detect GHSA-grg2-63fw-f2qr in my PyPI dependencies?

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.

How do I mitigate GHSA-grg2-63fw-f2qr if there is no patch (or I can't update yet)?

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.

How does O3 Security protect against GHSA-grg2-63fw-f2qr?

O3 pinpoints whether GHSA-grg2-63fw-f2qr is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Is GHSA-grg2-63fw-f2qr actively exploited in the wild?

No public exploit code has been indexed for GHSA-grg2-63fw-f2qr yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for GHSA-grg2-63fw-f2qr?

GHSA-grg2-63fw-f2qr has an EPSS (Exploit Prediction Scoring System) score of 0.4%, placing it in the 32th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

When was GHSA-grg2-63fw-f2qr published, and has it been updated?

GHSA-grg2-63fw-f2qr was published on January 13, 2026 and was last updated on June 8, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍 PyPI

GHSA-grg2-63fw-f2qr

MEDIUM

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

Also known asCVE-2026-22773PYSEC-2026-143

Published

Jan 13, 2026

Updated

Jun 8, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

EPSS Exploitation Probability

via FIRST.org ↗

0.4%probability of exploitation in next 30 days

Lower Risk32th percentile+0.38%

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

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

Users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination.

Details

The vulnerability is triggered when the image processor encounters a 1x1 pixel image with shape (1, 1, 3) in HWC (Height, Width, Channel) format. Due to the ambiguous dimensions, the processor incorrectly assumes the image is in CHW (Channel, Height, Width) format with shape (3, H, W). This misinterpretation causes an incorrect calculation of the number of image patches, resulting in a fatal tensor split operation failure.

Crash location: vllm/model_executor/models/idefics3.py line 672:

def _process_image_input(self, image_input: ImageInputs) -> torch.Tensor | list[torch.Tensor]:
    # ...
    num_patches = image_input["num_patches"]
    return [e.flatten(0, 1) for e in image_features.split(num_patches.tolist())]

The split() call fails because the computed num_patches value (17) does not match the actual tensor dimension (9):

RuntimeError: split_with_sizes expects split_sizes to sum exactly to 9 
(input tensor's size at dimension 0), but got split_sizes=[17]

This unhandled exception terminates the EngineCore process, crashing the server.

Affected Models

Any model using the Idefics3 architecture. The vulnerability was tested with HuggingFaceTB/SmolVLM-Instruct.

Impact

Denial of service by crashing the engine

Mitigation

Validating the input:

def _validate_image_dimensions(self, image_shape):
    h, w = image_shape[:2] if len(image_shape) == 3 else image_shape
    if h < MIN_IMAGE_SIZE or w < MIN_IMAGE_SIZE:
        raise ValueError(f"Image dimensions too small: {h}x{w}")

Managing the exception:

try:
    return [e.flatten(0, 1) for e in image_features.split(num_patches.tolist())]
except RuntimeError as e:
    logger.error(f"Image processing failed: {e}")
    raise InvalidImageError("Failed to process image features") from e

Fixes

https://github.com/vllm-project/vllm/pull/29881

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	≥ 0.6.4&&< 0.12.0	0.12.0

Detection & mitigation playbook

Open-source dependency

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.
Fix
Update vllm to 0.12.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-grg2-63fw-f2qr is resolved across your whole dependency graph.
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.
How O3 protects you
O3 pinpoints whether GHSA-grg2-63fw-f2qr 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-grg2-63fw-f2qr. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

### Summary Users can crash the vLLM engine serving multimodal models that use the _Idefics3_ vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. ### Details The vulnerability is triggered when the image processor encounters a 1x1 pixel image with shape (1, 1, 3) in HWC (Height, Width, Channel) format. Due to the ambiguous dimensions, the processor incorrectly assumes the image is in CHW (Channel, Height, Width) format with shape (3, H, W). This m

O3 Security · Impact-Aware SCA

Is GHSA-grg2-63fw-f2qr in your dependencies?

O3 detects GHSA-grg2-63fw-f2qr across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

Scan my dependencies How O3 SCA works