HighVulnerabilityLLM-specific
CVE-2025-62164: vLLM memory corruption through prompt embeddings in Completions API
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-62164
- Published
- Record updated
- Affected
- vllm >= 0.10.2, < 0.11.1
- Fixed in
- 0.11.1
- released November 18, 2025, 2 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 1.0%
Summary
vLLM versions 0.10.2 up to but not including 0.11.1 contain a memory corruption flaw in the Completions API endpoint. The endpoint calls torch.load() on user-supplied prompt embeddings without sufficient validation, and PyTorch 2.8.0 disables sparse tensor integrity checks by default, so crafted tensors can trigger an out-of-bounds write during to_dense(). The result is a crash (denial-of-service) and potentially code execution on the server hosting vLLM.
Mitigation
This issue has been patched in version 0.11.1.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents
Topics
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online