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

GHSA-rh4j-5rhw-hr54

HIGH

vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator

Also known asCVE-2025-24357PYSEC-2025-58
Published
Jan 27, 2025
Updated
Feb 4, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
0.6%probability of exploitation in next 30 days
Lower Risk46th percentile-0.36%
0.00%0.50%1.01%1.51%0.3%0.6%Dec 25Apr 26Jun 26

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

Description

The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It use torch.load function and weights_only parameter is default value False. There is a security warning on https://pytorch.org/docs/stable/generated/torch.load.html, when torch.load load a malicious pickle data it will execute arbitrary code during unpickling.

Impact

This vulnerability can be exploited to execute arbitrary codes and OS commands in the victim machine who fetch the pretrained repo remotely.

Note that most models now use the safetensors format, which is not vulnerable to this issue.

References

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllmall versions0.7.0

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 0.7.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-rh4j-5rhw-hr54 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-rh4j-5rhw-hr54 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-rh4j-5rhw-hr54. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

### Description The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It use torch.load function and weights_only parameter is default value False. There is a security warning on https://pytorch.org/docs/stable/generated/torch.load.html, when torch.load load a malicious pickle data it will execute arbitrary code during unpickling. ### Impact This vulnerability can be exploited to execute arbitrary codes and OS commands in the victim machine who fetch the pretrained repo remotely. Note that most models
O3 Security · Impact-Aware SCA

Is GHSA-rh4j-5rhw-hr54 in your dependencies?

O3 detects GHSA-rh4j-5rhw-hr54 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.