CVE-2026-34159 | ggml-org llama.cpp up to 55abc39/up to 55d4206c8/b7824 GRAPH_COMPUTE Message deserialize_tensor memory corruption (GHSA-j8rj-fmpv-wcxw)

VDB-354740 · CVE-2026-34159 · GHSA-J8RJ-FMPV-WCXW GGML-ORG LLAMA.CPP UP TO 55ABC39/UP TO 55D4206C8/B7824 GRAPH_COMPUTE MESSAGE DESERIALIZE_TENSOR MEMORY CORRUPTION HISTORYDIFFRELATEJSONXMLCTI CVSS Meta Temp Score Current Exploit Price (≈) CTI Interest Score 8.4 $0-$5k 1.20 Summaryinfo A vulnerability categorized as critical has been discovered in ggml-org llama.cpp. Affected by this issue is the function deserialize_tensor of the file llama.cpp of the component GRAPH_COMPUTE Message Handler. Such manipulation leads to memory corruption. This vulnerability is referenced as CVE-2026-34159. It is possible to launch the attack remotely. No exploit is available. It is advisable to upgrade the affected component. Detailsinfo A vulnerability was found in ggml-org llama.cpp and classified as critical. Affected by this issue is the function deserialize_tensor of the file llama.cpp of the component GRAPH_COMPUTE Message Handler. The manipulation with an unknown input leads to a memory corruption vulnerability. Using CWE to declare the problem leads to CWE-119. The product performs operations on a memory buffer, but it can read from or write to a memory location that is outside of the intended boundary of the buffer. Impacted is confidentiality, integrity, and availability. CVE summarizes: llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492. The advisory is shared for download at github.com. This vulnerability is handled as CVE-2026-34159 since 03/25/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. There are known technical details, but no exploit is available. Upgrading to version b8492 eliminates this vulnerability. Applying the patch 39bf0d3c6a95803e0f41aaba069ffbee26721042 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version. Productinfo Vendor ggml-org Name llama.cpp Version 55abc39 55d4206c8 b7824 License open-source Website Product: https://github.com/ggml-org/llama.cpp/ CPE 2.3info 🔒 🔒 CPE 2.2info 🔒 🔒 CVSSv4info VulDB Vector: 🔒 VulDB Reliability: 🔍 CVSSv3info VulDB Meta Base Score: 8.5 VulDB Meta Temp Score: 8.4 VulDB Base Score: 7.3 VulDB Temp Score: 7.0 VulDB Vector: 🔒 VulDB Reliability: 🔍 CNA Base Score: 9.8 CNA Vector (GitHub_M): 🔒 CVSSv2info Vector Complexity Authentication Confidentiality Integrity Availability Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock VulDB Base Score: 🔒 VulDB Temp Score: 🔒 VulDB Reliability: 🔍 Exploitinginfo Class: Memory corruption CWE: CWE-119 CAPEC: 🔒 ATT&CK: 🔒 Physical: No Local: No Remote: Yes Availability: 🔒 Status: Not defined Price Prediction: 🔍 Current Price Estimation: 🔒 0-Day Unlock Unlock Unlock Unlock Today Unlock Unlock Unlock Unlock Threat Intelligenceinfo Interest: 🔍 Active Actors: 🔍 Active APT Groups: 🔍 Countermeasuresinfo Recommended: Upgrade Status: 🔍 0-Day Time: 🔒 Upgrade: llama.cpp b8492 Patch: 39bf0d3c6a95803e0f41aaba069ffbee26721042 Timelineinfo 03/25/2026 CVE reserved 04/01/2026 +6 days Advisory disclosed 04/01/2026 +0 days VulDB entry created 04/01/2026 +0 days VulDB entry last update Sourcesinfo Product: github.com Advisory: GHSA-j8rj-fmpv-wcxw Status: Confirmed CVE: CVE-2026-34159 (🔒) GCVE (CVE): GCVE-0-2026-34159 GCVE (VulDB): GCVE-100-354740 Entryinfo Created: 04/01/2026 20:46 Changes: 04/01/2026 20:46 (69) Complete: 🔍 Cache ID: 99:A67:101 Discussion No comments yet. Languages: en. Please log in to comment. ◂ PreviousOverviewNext ▸