How severe is GHSA-pmqf-x6x8-p7qw?

GHSA-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw?

GHSA-pmqf-x6x8-p7qw affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-pmqf-x6x8-p7qw?

Update vllm to 0.11.1 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-pmqf-x6x8-p7qw is resolved across your whole dependency graph.

How do I detect GHSA-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw?

O3 pinpoints whether GHSA-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw actively exploited in the wild?

No public exploit code has been indexed for GHSA-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw?

GHSA-pmqf-x6x8-p7qw has an EPSS (Exploit Prediction Scoring System) score of 0.3%, placing it in the 25th 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-pmqf-x6x8-p7qw published, and has it been updated?

GHSA-pmqf-x6x8-p7qw was published on November 20, 2025 and was last updated on February 4, 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-pmqf-x6x8-p7qw

MEDIUM

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

Also known asCVE-2025-62372

Published

Nov 20, 2025

Updated

Feb 4, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

EPSS Exploitation Probability

via FIRST.org ↗

0.3%probability of exploitation in next 30 days

Lower Risk25th percentile+0.24%

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 by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page).

The issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5)

Details

Using image embeddings as an example:

For models that support image embedding inputs, the engine crashes when scattering the embeddings to inputs_embeds (mismatched shape)
For models that don't support image embedding inputs, the engine crashes when validating the inputs inside get_input_embeddings (validation fails).

This happens because we only validate ndim of the tensor, but not the full shape, in input processor (via MultiModalDataParser).

Impact

Denial of service by crashing the engine

Mitigation

Use API key to limit access to trusted users.
Set --limit-mm-per-prompt to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.

Resolution

https://github.com/vllm-project/vllm/pull/27204

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	≥ 0.5.5&&< 0.11.1	0.11.1

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 0.11.1 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw 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-pmqf-x6x8-p7qw. 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 by passing multimodal embedding inputs with correct `ndim` but incorrect `shape` (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). The issue has existed ever since we added support for image embedding inputs, i.e. #6613 (released in v0.5.5) ### Details Using image embeddings as an example: - For models that support image embedding inputs, the engine crashes when scattering the embeddings to `inputs_embeds` (mismatched shape) -

O3 Security · Impact-Aware SCA

Is GHSA-pmqf-x6x8-p7qw in your dependencies?

O3 detects GHSA-pmqf-x6x8-p7qw 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