GHSA-ggpf-24jw-3fcw
CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0
Description
https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weights_only=True to calls to torch.load() did not solve the problem prior to PyTorch 2.6.0.
PyTorch has issued a new CVE about this problem: https://github.com/advisories/GHSA-53q9-r3pm-6pq6
This means that versions of vLLM using PyTorch before 2.6.0 are vulnerable to this problem.
Background Knowledge
When users install VLLM according to the official manual
But the version of PyTorch is specified in the requirements. txt file
So by default when the user install VLLM, it will install the PyTorch with version 2.5.1
In CVE-2025-24357, weights_only=True was used for patching, but we know this is not secure. Because we found that using Weights_only=True in pyTorch before 2.5.1 was unsafe
Here, we use this interface to prove that it is not safe.
Fix
update PyTorch version to 2.6.0
Credit
This vulnerability was found By Ji'an Zhou and Li'shuo Song
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
What each source reports
GitHub Advisories Score used
CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0
Description
https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weights_only=True to calls to torch.load() did not solve the problem prior to PyTorch 2.6.0.
PyTorch has issued a new CVE about this problem: https://github.com/advisories/GHSA-53q9-r3pm-6pq6
This means that versions of vLLM using PyTorch before 2.6.0 are vulnerable to this problem.
Background Knowledge
When users install VLLM according to the official manual
But the version of PyTorch is specified in the requirements. txt file
So by default when the user install VLLM, it will install the PyTorch with version 2.5.1
In CVE-2025-24357, weights_only=True was used for patching, but we know this is not secure. Because we found that using Weights_only=True in pyTorch before 2.5.1 was unsafe
Here, we use this interface to prove that it is not safe.
Fix
update PyTorch version to 2.6.0
Credit
This vulnerability was found By Ji'an Zhou and Li'shuo Song
- Record
GHSA-ggpf-24jw-3fcw- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-1395
- Updated
- 2026-11-02
OSV
CVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0
Description
https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 reported a vulnerability where loading a malicious model could result in code execution on the vllm host. The fix applied to specify weights_only=True to calls to torch.load() did not solve the problem prior to PyTorch 2.6.0.
PyTorch has issued a new CVE about this problem: https://github.com/advisories/GHSA-53q9-r3pm-6pq6
This means that versions of vLLM using PyTorch before 2.6.0 are vulnerable to this problem.
Background Knowledge
When users install VLLM according to the official manual
But the version of PyTorch is specified in the requirements. txt file
So by default when the user install VLLM, it will install the PyTorch with version 2.5.1
In CVE-2025-24357, weights_only=True was used for patching, but we know this is not secure. Because we found that using Weights_only=True in pyTorch before 2.5.1 was unsafe
Here, we use this interface to prove that it is not safe.
Fix
update PyTorch version to 2.6.0
Credit
This vulnerability was found By Ji'an Zhou and Li'shuo Song
- Record
GHSA-ggpf-24jw-3fcw- CVSS 3.1
- 9.8 Critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-1395
- Updated
- 2026-11-02
Affected packages
| Package | Affected | Fixed |
|---|---|---|
vllmPyPI | before 0.8.0 | 0.8.0 |
vllmPyPI | before 0.8.0, plus listed versions 0.0.10.1.00.1.10.1.20.1.3 Show 45 moreShow less0.1.40.1.50.1.60.1.70.2.00.2.10.2.1.post10.2.20.2.30.2.40.2.50.2.60.2.70.3.00.3.10.3.20.3.30.4.00.4.0.post10.4.10.4.20.4.30.5.00.5.0.post10.5.10.5.20.5.30.5.3.post10.5.40.5.50.6.00.6.10.6.1.post10.6.1.post20.6.20.6.30.6.3.post10.6.40.6.4.post10.6.50.6.60.6.6.post10.7.00.7.10.7.2 | 0.8.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | GitHub Advisories, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
GHSA-ggpf-24jw-3fcw is a critical vulnerability (CVSS 9.8) in vllm, published April 23, 2025. No source lists public exploit code. Fixed in vllm 0.8.0.
References
Left out here: 1 version. The JSON record has them.