CVE-2025-52566
Ggml Llama.cpp buffer overflow
- Published24 Jun 2025
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
CVSS 3.1 breakdown
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:HAffected products
Remediation
References
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2025-52566 being actively exploited?
CVE-2025-52566 is not in the CISA KEV catalog. A public exploit reference exists, so treat it as exploitable. Its EPSS exploit probability is 0.36%.
How severe is CVE-2025-52566?
CVE-2025-52566 has a CVSS 3.1 base score of 8.6, rated high. EPSS estimates a 0.36% probability of exploitation.
Which products are affected by CVE-2025-52566?
Affected products include Ggml Llama.cpp.
How do I fix CVE-2025-52566?
Upgrade affected software to a fixed version, for example Ggml Llama.cpp b5721 or later, then confirm no affected versions remain in your inventory.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2025-52566 against the real software inventory on every managed device, every day. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.