GHSA-rh4j-5rhw-hr54 CVE-2025-24357 PYSEC-2025-58
vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
- Severity
- 7.5 / 10
- High · CVSS 3.1
- Exploit chance (EPSS)
- 0.87%
- Chance of exploitation in the next 30 days. Higher than 58.76% of scored vulnerabilities.
- Known exploited
- No
- Not in CISA's catalog
- Weakness
- CWE-502 Deserialization of Untrusted Data
- Fix
0.7.0- Upgrade vllm to this version or later
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 versions
PyPI
How to fix
Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.
vllm PyPI → 0.7.0
- pip
pip install --upgrade "vllm>=0.7.0"- poetry
poetry add "vllm>=0.7.0"- uv
uv add "vllm>=0.7.0"
Severity breakdown
CVSS 3.1 7.5
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
- Attack vector
- Network
- Attack complexity
- High
- Privileges required
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Weakness
CWE-502: Deserialization of Untrusted Data
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
How to prevent it
- Architecture and Design, Implementation: If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
- Implementation: When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
- Implementation: Explicitly define a final object() to prevent deserialization.
- Architecture and Design, Implementation: Make fields transient to protect them from deserialization. An attempt to serialize and then deserialize a class containing transient fields will result in NULLs where the transient data should be. This is an excellent way to prevent time, environment-based, or sensitive variables from being carried over and used improperly.
- Implementation: Avoid having unnecessary types or gadgets (a sequence of instances and method invocations that can self-execute during the deserialization process, often found in libraries) available that can be leveraged for malicious ends. This limits the potential for unintended or unauthorized types and gadgets to be leveraged by the attacker. Add only acceptable classes to an allowlist. Note: new gadgets are constantly being discovered, so this alone is not a sufficient mitigation.
- Architecture and Design, Implementation: Employ cryptography of the data or code for protection. However, it's important to note that it would still be client-side security. This is risky because if the client is compromised then the security implemented on the client (the cryptography) can be bypassed.
- Operation: Use an application firewall that can detect attacks against this weakness. It can be beneficial in cases in which the code cannot be fixed (because it is controlled by a third party), as an emergency prevention measure while more comprehensive software assurance measures are applied, or to provide defense in depth [REF-1481].
References
Advisories
Packages
Other links
- github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54
- github.com/vllm-project/vllm/pull/12366
- github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-58.yaml
- github.com/vllm-project/vllm/releases/tag/v0.7.0
- pytorch.org/docs/stable/generated/torch.load.html
Timeline
- Published
- Last updated by the source
- Latest EPSS score
Related advisories
| Advisory | Severity | Why it's related |
|---|---|---|
| GHSA-8397-8qf6-f2gm vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine | Medium | Also affects vllm |
| GHSA-x567-49g5-p4cf vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs | Medium | Also affects vllm |
| GHSA-vvpg-rrww-wpmh vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server | Medium | Also affects vllm |
| GHSA-q97c-p368-75c4 vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) | Medium | Also affects vllm |
| GHSA-h3rc-j82p-2c3h vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE | High | Also affects vllm |
| GHSA-gq5q-89c7-vhvx vLLM DeepSeek-OCR image processing vulnerable to denial of service | Medium | Also affects vllm |
| GHSA-6757-hggm-hp2w vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled | High | Also affects vllm |
| GHSA-542m-9234-8gvf vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool | Medium | Also affects vllm |
MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.
Check your repos with MergeHarbor