CVE-2025-24357
Essential information
- Published
- 27/01/2025 18:15
- Modified
- 27/01/2025 18:15
- Author
- —
- Creator
- —
- CVSS
- 7.5 HIGH (v3.1)
- CISA KEV
- No
- CWE
- —
- CVSS vector
-
—
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H—
CVSS metrics
- Access vector
- —
- Access complexity
- —
- Authentication
- —
- Confidentiality impact
- —
- Integrity impact
- —
- Availability impact
- —
- Exploitability
- —
- Remediation level
- —
- Report confidence
- —
- Temporal score
- —
- Attack vector
- NETWORK
- Attack complexity
- HIGH
- Privileges required
- NONE
- User interaction
- REQUIRED
- Scope
- UNCHANGED
- Confidentiality impact
- HIGH
- Integrity impact
- HIGH
- Availability impact
- HIGH
- Exploit code maturity
- —
- Remediation level
- —
- Report confidence
- —
- Temporal score
- —
- Attack vector
- —
- Attack complexity
- —
- Attack requirements
- —
- Privileges required
- —
- User interaction
- —
- Confidentiality (V)
- —
- Confidentiality (S)
- —
- Integrity (V)
- —
- Integrity (S)
- —
- Availability (V)
- —
- Availability (S)
- —
- Exploit maturity
- —
Description
vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.
NVD status
- Status
- Awaiting Analysis — CVE has been recently published to the CVE List and has been received by the NVD.
- Source
- [email protected]
- NVD
- View on NVD