Lucene search
+L

128 matches found

EUVD
EUVD
added 3 days ago6 views

EUVD-2026-54281

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit function where unchecked multiplications in malloc calls can wrap past INT32MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causin...

8.5CVSS6.5AI score0.00139EPSS
SaveExploits0References2
EUVD
EUVD
added 3 days ago6 views

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...

9.2CVSS6.5AI score0.00619EPSS
SaveExploits0References2
EUVD
EUVD
added 3 days ago6 views

EUVD-2026-54285

llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with a...

6.5CVSS5.5AI score0.00453EPSS
SaveExploits0References4
UbuntuCve
UbuntuCve
added 3 days ago12 views

CVE-2026-43627

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit function where unchecked multiplications in malloc calls can wrap past INT32MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causin...

8.5CVSS6.2AI score0.00139EPSS
SaveExploits0References2
OSV
OSV
added 4 days ago5 views

DEBIAN-CVE-2026-43632

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints /tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens that bypass the task queue and access ctxserver.vocab directly on HTTP...

9.2CVSS6AI score0.0033EPSS
SaveExploits0References1
OSV
OSV
added 4 days ago6 views

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...

9.2CVSS6.3AI score0.00619EPSS
SaveExploits0References1
Cvelist
Cvelist
added 4 days ago34 views

CVE-2026-43632 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints /tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens that bypass the task queue and access ctxserver.vocab directly on HTTP...

9.2CVSS0.0033EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 4 days ago11 views

CVE-2026-43632 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints /tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens that bypass the task queue and access ctxserver.vocab directly on HTTP...

9.2CVSS5.9AI score0.0033EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 4 days ago6 views

CVE-2026-43631 llama.cpp b7492–b9060 Use-After-Free RCE via llama-server

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending...

9.2CVSS6.3AI score0.00412EPSS
SaveExploits0References2
CVE
CVE
added 4 days ago29 views

CVE-2026-43630

CVE-2026-43630 affects llama.cpp builds b5702–b7653, where an out-of-bounds read in the recurrent memory state restore path can be triggered by attackers with write access to the slot save directory. By crafting a malicious slot file with an oversized seq_id, an out-of-bounds read may leak heap d...

6.5CVSS5.5AI score0.00453EPSS
SaveExploits0References4
Cvelist
Cvelist
added 4 days ago26 views

CVE-2026-43630 llama.cpp b5702–b7653 Out-of-Bounds Read Information Disclosure

llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with a...

6.5CVSS0.00453EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
added 4 days ago9 views

CVE-2026-43630 llama.cpp b5702–b7653 Out-of-Bounds Read Information Disclosure

llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with a...

6.5CVSS5.3AI score0.00453EPSS
SaveExploits0References4
Cvelist
Cvelist
added 4 days ago27 views

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...

9.2CVSS0.00619EPSS
SaveExploits0References2
Cvelist
Cvelist
added 4 days ago38 views

CVE-2026-43627 llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit function where unchecked multiplications in malloc calls can wrap past INT32MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causin...

8.5CVSS0.00139EPSS
SaveExploits0References2
CVE
CVE
added 4 days ago29 views

CVE-2026-43627

The CVE-2026-43627 issue affects llama.cpp (b1283–b9058) in the llama_batch_init() function, where unchecked multiplications in malloc() cause allocation sizes to wrap past INT32_MAX. This leads to heap corruption and can potentially enable arbitrary code execution through subsequent batch operat...

8.5CVSS6.5AI score0.00139EPSS
SaveExploits0References2
Cvelist
Cvelist
added 4 days ago27 views

CVE-2026-70639 llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp

llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench1model function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger ...

6.8CVSS0.0013EPSS
SaveExploits0References4
CVE
CVE
added 4 days ago43 views

CVE-2026-43622

CVE-2026-43622 affects llama.cpp builds b1886–b7445, where the LLaMA-Android JNI wrapper presents a double free vulnerability. The code allocates memory with malloc() in new_1batch() but frees it with the C++ delete operator in free_1batch(), leading to heap metadata corruption. Consequences desc...

8.5CVSS6.3AI score0.00134EPSS
SaveExploits0References4
NVD
NVD
added 2026/07/27 1:16 a.m.12 views

CVE-2026-17501

A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes uncontrolled recursion. The attack may be initiated remotely. The pull...

6.9CVSS0.00419EPSS
SaveExploits0References7
Tenable Nessus
Tenable Nessus
added 2026/05/20 12:0 a.m.12 views

Linux Distros Unpatched Vulnerability : CVE-2026-34159

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor'...

9.8CVSS6.4AI score0.01126EPSS
SaveExploits2References2
EUVD
EUVD
added 2026/04/01 4:59 p.m.8 views

EUVD-2026-17975

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserializetensor skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPHCOMPUTE messages. Combined...

9.8CVSS6.2AI score0.01126EPSS
SaveExploits2References3
Rows per page
Query Builder