Vuln Signal Radar
public-safe defensive signal
Agent JSON
MEDIUMpublic-safe

CVE-2026-105756

NVD: vLLM is an inference and serving engine for large language models. NVD: Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. NVD: On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent...

CVSS
6.5 Severity
MEDIUM EPSS
0.0031 (22) KEV
-

Source-published summary

NVD: vLLM is an inference and serving engine for large language models. NVD: Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. NVD: On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent...

Possible impact

Source describes service availability risk. Possible impact: The affected service may become unavailable or unreliable.

Affected context

vendor/product: vllm / vllm

Remediation / advisory

Patch confirmed by source text; fixed version context: 0.30.0..

Why it matters

Source describes service availability risk. Possible impact: The affected service may become unavailable or unreliable.; CVSS 6.5 (MEDIUM); EPSS percentile 22; not listed in KEV; Patch confirmed by source text; fixed version context: 0.30.0; sources: NVD, OSV, Vendor Advisory.

What to verify

Confirm affected product/version, vendor advisory, patch or mitigation, and exposure.

Exposure hint

exposure unknown

Impact tags

service availability review

Urgency reasons

affected product presentvendor advisory presentrecent updateremediation reference present

Source-derived note

Summary derived from NVD / OSV / Vendor Advisory description; unsafe procedural detail is not shown.

Redaction metadata

source summary used
True
fallback summary used
False
unsafe procedural detail present
false
raw source displayed
false
public summary redacted
true

Remediation handoff

Public-safe static handoff for human/Codex remediation planning. Scan, patch, external execution, and auto remediation are disabled.

Handoff JSON Handoff Markdown Safe Codex prompt

Safety note

This radar shows source-published defensive context only. Exploit procedures, exploit strings, scanner commands, and auto-remediation are not provided.

Official references