CVE-2026-133710: high-severity vulnerability in ggml-org llama.cpp
llama.cpp b11003 before b12556 Heap Out-of-Bounds Write via hrm_text Model Loader
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.5epss 0.3%
llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Affected products
ggml-org · llama.cppRelated CVEs — ggml-org llama.cpp
In the same product, most dangerous first.
CVE-2026-34159CRITICALllama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backendEPSS 1.7%CVE-2026-78148MEDIUMggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_compute null pointer dereferenceEPSS 0.7%CVE-2026-17501MEDIUMggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursionEPSS 0.7%CVE-2026-17500MEDIUMggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereferenceEPSS 0.7%CVE-2026-86317MEDIUMggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertionEPSS 0.7%CVE-2026-43629CRITICALllama.cpp b4882–b9058 Buffer Overflow in KV Cache State RestoreEPSS 0.7%