Code execution via unsafe checkpoint deserialization
Published Jan 27, 2025 · Updated Feb 12, 2025
Deserialization in vLLM before 0.7.0 allows remote attackers to execute code by causing a malicious model checkpoint to load. hf_model_weights_iterator passes downloaded PyTorch checkpoint files to torch.load without weights_only=True, so pickle opcodes execute during unpickling. Exploitation requires a user or deployment to fetch an attacker-controlled pretrained repository; safetensors models do not expose this path.
Summary
What happened
Deserialization in vLLM before 0.7.0 allows remote attackers to execute code by causing a malicious model checkpoint to load. hf_model_weights_iterator passes downloaded PyTorch checkpoint files to torch.load without weights_only=True, so pickle opcodes execute during unpickling. Exploitation requires a user or deployment to fetch an attacker-controlled pretrained repository; safetensors models do not expose this path.
The record
- CVE
- CVE-2025-24357
- Published
- Jan 27, 2025
- Updated
- Feb 12, 2025
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-502, T1204.002
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jan 27, 2025CVE publishedPublication date reported by the CVE source.
- Feb 12, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.7.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo