01 Record
CVE-2025-47277
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
CriticalPUBLISHEDCNA: GitHub_M
CNA base score9.8 CVSS v3.xCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
02 Description
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
03 Exploitation and scoring
- Exploitation
- Assessed, none found. CISA's assessment recorded neither public exploit code nor evidence of exploitation when it was made.
- SSVC decision
- ExploitationnoneCISA recorded no public exploit code and no evidence of exploitation.
- AutomatableyesAn attacker can reliably automate reconnaissance through exploitation, so this scales.
- Technical ImpacttotalSuccessful exploitation gives total control of the vulnerable component.
- EPSS probability
- 0.96% probability of exploitation activity in the next 30 days.
- EPSS percentile
- Equal to or higher than the score of 61.4% of scored records. A rank, not a probability.
- NVD base score
- 9.8 (CVSS v3.x), scored by the NVD independently of the CNA.
- NVD CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- NVD analysis status
- Analyzed. NVD last modified this record on 2026-06-17.
- Red Hat severity
- Moderate. Red Hat's rating for its own products, not a CVSS rating.
Exploit-prediction scores from FIRST. Independent scoring and analysis status from the NVD. Vendor severity from Red Hat. Exploitation assessment and catalog membership from CISA.
04 Metadata
- Published
- 2025-05-20 17:32Z1 YR AGO
- Last updated
- 2025-05-20 17:52Z1 YR AGO
- Reserved
- 2025-05-05
- Assigning CNA
- GitHub_M
- Record state
- PUBLISHED
- Severity
- Critical (CVSS 9.8)
- CNA CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Weaknesses
- CWE-502Deserialization of Untrusted DataBase
- Data version
- 5.1
- Document digest
- a142b32a3f70271a5881ebb00e8eb5d4b6a6cc6b781bcf7e1bca9adef46ee8cc
05 Affected products
VendorProductVersionsPlatforms
06 References
- github.comhttps://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv
- github.comhttps://github.com/vllm-project/vllm/pull/15988
- github.comhttps://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7
- docs.vllm.aihttps://docs.vllm.ai/en/latest/deployment/security.html