PYSEC-2026-4308 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the tool-continuation re-submission has omitted the salt. Summary On the GPT-OSS "Harmony" path POST...

PYSEC-2026-4306 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the loose cachesalt validator and unguarded scheduling-path lookup reach. Summary vLLM's OpenAI-compatible...

GHSA-935W-9G4M-P28P vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the tool-continuation re-submission has omitted the salt. Summary On the GPT-OSS "Harmony" path POST...

vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the tool-continuation re-submission has omitted the salt. Summary On the GPT-OSS "Harmony" path POST...

Uncaught Exception

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Uncaught Exception via the cachesalt parameter in request protocol handlers across multiple entrypoints chat completion, completion, responses,...

GHSA-2823-QMQ8-RWVJ vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the loose cachesalt validator and unguarded scheduling-path lookup reach. Summary vLLM's OpenAI-compatible...

EUVD-2026-92846

vLLM: Loose cachesalt validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream ValueError denial of service...

vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the loose cachesalt validator and unguarded scheduling-path lookup reach. Summary vLLM's OpenAI-compatible...

CVE-2026-105756

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105752

The vLLM inference and serving engine is vulnerable in versions prior to 0.30.0 due to a flaw in how Harmony tool continuations are handled via POST /v1/responses requests. The application fails to preserve the cache_salt value when rebuilding the next-turn engine input, causing the continuation ...

CVE-2026-105752 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cachesalt value, placing the continuation prefix in the global unsalted cache...

CVE-2026-105752: Exposure of Sensitive Information to an Unauthorized Actor

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cachesalt value, placing the continuation prefix in the global unsalted cache...

CVE-2026-105756: Improper Input Validation

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the cachesalt field across multiple API protocol handlers Anthropic, OpenAI chat completion...

CVE-2026-100647

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cachesalt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP...

CVE-2026-100647

A flaw was found in vLLM. An unauthenticated remote attacker can cause a Denial of Service DoS by sending HTTP requests containing an excessively large cachesalt parameter to exposed API endpoints. Because this input lacks maximum length validation, processing the oversized data consumes excessiv...

CVE-2026-100647 vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cachesalt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP...

CVE-2026-100647 vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cachesalt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP...