CVE-2025-49847
CVE-2025-49847 is a high-severity vulnerability in Ggml Llama.cpp with a CVSS 3.x base score of 8.8. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-119.
Key facts
- Severity: High (CVSS 3.x base score 8.8)
- EPSS exploit prediction: 0% (36th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2025-18632
- Weakness: CWE-119
- Affected product: Ggml Llama.cpp
- Published:
- Last modified:
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
Frequently asked questions
- What is CVE-2025-49847?
- llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
- How severe is CVE-2025-49847?
- CVE-2025-49847 has a CVSS 3.x base score of 8.8, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is high, integrity high, and availability high.
- Is CVE-2025-49847 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (36th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2025-49847?
- CVE-2025-49847 affects Ggml Llama.cpp. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2025-49847?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2025-49847 have an EU (EUVD) identifier?
- Yes. CVE-2025-49847 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-18632.
- When was CVE-2025-49847 published?
- CVE-2025-49847 was published on 2025-06-17 and last updated on 2026-06-17.
References
- https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5
- https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr
Affected products (1)
- cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*
More vulnerabilities in Ggml Llama.cpp
- CVE-2024-42479 — Critical (CVSS 10.0): llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause…
- CVE-2026-34159 — Critical (CVSS 9.8): llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's…
- CVE-2026-21869 — High (CVSS 8.8): llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is…
- CVE-2024-23605 — High (CVSS 8.8): A heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality of llama.cpp Commit…
- CVE-2024-23496 — High (CVSS 8.8): A heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str functionality of llama.cpp Commit…
- CVE-2024-21836 — High (CVSS 8.8): A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp…
All CVEs affecting Ggml Llama.cpp →
Other CWE-119 (Improper Restriction of Operations within the Bounds of a Memory Buffer) vulnerabilities
- CVE-2026-2778 — Critical (CVSS 10.0): Sandbox escape due to incorrect boundary conditions in the DOM: Core & HTML component. This vulnerability was fixed in…
- CVE-2026-2776 — Critical (CVSS 10.0): Sandbox escape due to incorrect boundary conditions in the Telemetry component in External Software. This vulnerability…
- CVE-2025-1866 — Critical (CVSS 10.0): Improper Restriction of Operations within the Bounds of a Memory Buffer vulnerability in warmcat libwebsockets allows…
- CVE-2022-27625 — Critical (CVSS 10.0): A vulnerability regarding improper restriction of operations within the bounds of a memory buffer is found in the…
- CVE-2022-27624 — Critical (CVSS 10.0): A vulnerability regarding improper restriction of operations within the bounds of a memory buffer is found in the…
- CVE-2020-11896 — Critical (CVSS 10.0): The Treck TCP/IP stack before 6.0.1.66 allows Remote Code Execution, related to IPv4 tunneling.