EUVD-2026-54284

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

DEBIAN-CVE-2026-43629

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

UBUNTU-CVE-2026-43629

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

CVE-2026-43629 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

CVE-2026-43629 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata function computes write size without overflow checking, allowing attackers with write access to the slotsavepath directory to corrupt heap memory. Attackers...

vLLM Allows Remote Code Execution via PyNcclPipe Communication Service

Impacted EnvironmentsThis issue ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. SummaryvLLM supports the use of thePyNcclPipeclass to establish a peer-to-peer communication domain for data transmission between...

PT-2026-53636

Impacted Environments This issue ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. Summary vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission...

LMCache: 16-bit multimodal hash collision can poison KV cache entries

A flaw has been found in LMCache up to 0.4.6. This affects the function hexhashtoint16 of the file lmcache/integration/vllm/utils.py of the component KV Cache Handler. Executing a manipulation can lead to use of weak hash. The attack needs to be launched locally. The attack requires a high level ...

Use of Weak Hash

Overview lmcache is an A LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios. Affected versions of this package are vulnerable to Use of Weak Hash in the hexhashtoint16 function of the KV Cache Handler process. An attacker can compromise da...

CVE-2026-10813

A flaw has been found in LMCache up to 0.4.6. This affects the function hexhashtoint16 of the file lmcache/integration/vllm/utils.py of the component KV Cache Handler. Executing a manipulation can lead to use of weak hash. The attack needs to be launched locally. The attack requires a high level ...

CVE-2026-10813 LMCache KV Cache utils.py hex_hash_to_int16 weak hash

A flaw has been found in LMCache up to 0.4.6. This affects the function hexhashtoint16 of the file lmcache/integration/vllm/utils.py of the component KV Cache Handler. Executing a manipulation can lead to use of weak hash. The attack needs to be launched locally. The attack requires a high level ...

CVE-2026-10813

A flaw has been found in LMCache up to 0.4.6. This affects the function hexhashtoint16 of the file lmcache/integration/vllm/utils.py of the component KV Cache Handler. Executing a manipulation can lead to use of weak hash. The attack needs to be launched locally. The attack requires a high level ...

CVE-2026-10813

Technical details about CVE-2026-10813 are not publicly available in the provided documents. Monitor for updates from LMCache advisories for affected components, impact, and patch availability.

CVE-2026-10813 LMCache KV Cache utils.py hex_hash_to_int16 weak hash

A flaw has been found in LMCache up to 0.4.6. This affects the function hexhashtoint16 of the file lmcache/integration/vllm/utils.py of the component KV Cache Handler. Executing a manipulation can lead to use of weak hash. The attack needs to be launched locally. The attack requires a high level ...

LMCache 安全漏洞

LMCache is an open-source large-scale caching tool developed by LMCache. Versions of LMCache 0.4.6 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the hexhashtoint16 function in the KV Cache Handler component’s lmcache/integration/vllm/utils.py file, which used ...

PYSEC-2026-2306

A vulnerability was found in vllm up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is...

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical copy without integrity protection. Using software fault...

CVE-2025-60455

Unsafe Deserialization vulnerability in Modular Max Serve before 25.6, specifically when the "--experimental-enable-kvcache-agent" feature is used allowing attackers to execute arbitrary code...

Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value KV cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection MTI, a modular framework that systematically perturbs cached key...

CVE-2025-47277

vLLM, an inference and serving engine for large language models LLMs, has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of...