TI-2025-29277 Aliases CVE-2025-46560 GHSA-vc6m-hm49-g9qg

vLLM phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service

HIGH 66CWE-1333Published 2025-04-30 · Updated 2025-04-30

Key facts

Attack vector: Network
Privileges required: None
User interaction: None
Attack complexity: Low
Impact type: Denial of service
Confidentiality · integrity · availability: None · None · High
Fix status: Fixed

Attack profile from CVSS 3.1 · NVD. Fix status from CNA and GitHub. Impact type from CWE-1333.

Summary

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV

EPSS 0.00533 45th percentileScored 2026-11-07

Public exploit Yes 1 exploit referenceTagged by NVD

Fix Fixed vllm (vllm-project): 0.8.5vllm (PyPI): 0.8.5

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation: Poc
Automatable: No
Technical impact: Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

Vendor	Product	Affected versions	Fixed in	Status	Source
vllm-project	vllm	0.8.0 to before 0.8.5	0.8.5	Patch available	CNA
—	vllm (PyPI)	0.8.0 to before 0.8.5	0.8.5	Patch available	GHSA-vc6m-hm49-g9qg

vllm Vendorvllm-project Affected 0.8.0 to before 0.8.5 Fixed in 0.8.5 Patch available CNA
vllm (PyPI) Vendor— Affected 0.8.0 to before 0.8.5 Fixed in 0.8.5 Patch available GHSA-vc6m-hm49-g9qg

CPE configurations NVD · 1

CPE	Versions	Role	Vendor
cpe:2.3:a:vllm:vllm::::::::	0.8.0 to before 0.8.5	Vulnerable	vLLM

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.8.0 to before 0.8.5 Vulnerable ·vLLM

Remediation

Fix · CNA vllm (vllm-project) Fixed in 0.8.5
Fix · GHSA-vc6m-hm49-g9qg vllm (PyPI) Fixed in 0.8.5 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

Not affected: 1 product

Red Hat Enterprise Linux AI (RHEL AI)

Timeline

2026-10-02 Threatist record created from CVE-2025-46560
2026-10-03 Alias added: GHSA-vc6m-hm49-g9qg

References

Exploit 1

https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg

Advisory 2

Other 4

TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5

See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences