CVE-2026-52130

Published Sep 1, 2026

Last updated 2 days ago

CVSS high 7.5

Overview

Description
llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.
Source
cve@mitre.org
NVD status
Analyzed
Products
llama.cpp

Risk scores

CVSS 3.1

Type
Secondary
Base score
7.5
Impact score
3.6
Exploitability score
3.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Severity
HIGH

Weaknesses

134c704f-9b21-4f2e-91b3-4a467353bcc0
CWE-674

Social media

Hype score
Not currently trending

Configurations

Related CVEs

  1. llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::bad_alloc and HTTP 500) via a negative top_n value in a POST request to /rerank.•CVE-2026-52132
  2. llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.•CVE-2026-52131
  3. llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap metadata corruption. Attackers can trigger this memory management mismatch to cause denial of service through process crashes or potentially achieve arbitrary code execution depending on allocator state.•CVE-2026-43622
  4. 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.•CVE-2026-34159
  5. llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.•CVE-2026-33298

References

Sources include official advisories and independent security research.