How severe is GHSA-c65p-x677-fgj6?

GHSA-c65p-x677-fgj6 has a CVSS score of 4.2/10, rated MEDIUM. Review your exposure and patch according to your risk tolerance.

Which packages are affected by GHSA-c65p-x677-fgj6?

GHSA-c65p-x677-fgj6 affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-c65p-x677-fgj6?

Update vllm to 0.9.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-c65p-x677-fgj6 is resolved across your whole dependency graph.

How do I detect GHSA-c65p-x677-fgj6 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-c65p-x677-fgj6 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-c65p-x677-fgj6?

O3 pinpoints whether GHSA-c65p-x677-fgj6 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-c65p-x677-fgj6 actively exploited in the wild?

No public exploit code has been indexed for GHSA-c65p-x677-fgj6 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-c65p-x677-fgj6?

GHSA-c65p-x677-fgj6 has an EPSS (Exploit Prediction Scoring System) score of 0.3%, placing it in the 18th 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.

What type of vulnerability is GHSA-c65p-x677-fgj6?

GHSA-c65p-x677-fgj6 is classified as CWE-1023 (CWE-1023), CWE-1288 (CWE-1288). These weakness types describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was GHSA-c65p-x677-fgj6 published, and has it been updated?

GHSA-c65p-x677-fgj6 was published on May 28, 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-c65p-x677-fgj6

MEDIUM

vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

Also known asCVE-2025-46722PYSEC-2025-43

Published

May 28, 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 Risk18th percentile+0.04%

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

In the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks.

Details

Affected file: vllm/multimodal/hasher.py
Affected method: MultiModalHasher.serialize_item https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35
Current behavior: For Image.Image instances, only obj.tobytes() is used for hashing.
Problem description: obj.tobytes() does not include the image’s width, height, or mode metadata.
Impact: Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in:
- Incorrect cache hits, leading to abnormal responses
- Deliberate construction of images with different meanings but the same hash value

Recommendation

In the serialize_item method, serialization of Image.Image objects should include not only pixel data, but also all critical metadata—such as dimensions (size), color mode (mode), format, and especially the info dictionary. The info dictionary is particularly important in palette-based images (e.g., mode 'P'), where the palette itself is stored in info. Ignoring info can result in hash collisions between visually distinct images with the same pixel bytes but different palettes or metadata. This can lead to incorrect cache hits or even data leakage.

Summary:
Serializing only the raw pixel data is insecure. Always include all image metadata (size, mode, format, info) in the hash calculation to prevent collisions, especially in cases like palette-based images.

Impact for other modalities For the influence of other modalities, since the video modality is transformed into a multi-dimensional array containing the length, width, time, etc. of the video, the same problem exists due to the incorrect sequence of numpy as well.

For audio, since the momo function is not enabled in librosa.load, the loaded audio is automatically encoded into single channels by librosa and returns a one-dimensional array of numpy, thus keeping the structure of numpy fixed and not affected by this issue.

Fixes

https://github.com/vllm-project/vllm/pull/17378

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	≥ 0.7.0&&< 0.9.0	0.9.0

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 0.9.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-c65p-x677-fgj6 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-c65p-x677-fgj6 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-c65p-x677-fgj6. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

## Summary In the file `vllm/multimodal/hasher.py`, the `MultiModalHasher` class has a security and data integrity issue in its image hashing method. Currently, it serializes `PIL.Image.Image` objects using only `obj.tobytes()`, which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. ## Details - **Af

O3 Security · Impact-Aware SCA

Is GHSA-c65p-x677-fgj6 in your dependencies?

O3 detects GHSA-c65p-x677-fgj6 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