UTC

llama.cpp

By ggml. 31 published vulnerabilities.

Advisories
31
Critical
5
Exploited in the wild
None listed
Latest
2026-09-01
Vulnerabilities
SeverityVulnerabilityPublishedFixed in
Highllama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::badalloc and HTTP 500) via a negative topn value in a POST request to /rerank.CVE-2026-521322026-09-01See advisory
Highllama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.CVE-2026-521312026-09-01See advisory
Highllama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.CVE-2026-521302026-09-01See advisory
Highllama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench1model() and free1context() lack synchronization, allowing Thread A to operate on freed memory while…CVE-2026-706402026-08-06See advisory
Mediumllama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer before dereferencing it.CVE-2026-706392026-08-06See advisory
Highllama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new1batch() function multiplies sizeof(llamaseqid) by an attacker-controlled nseqmax parameter without overflow…CVE-2026-706382026-08-06See advisory
Criticalllama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens) that…CVE-2026-436322026-08-06See advisory
Criticalllama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary…CVE-2026-436312026-08-06See advisory
Mediumllama.cpp builds b4882 before b8487 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated…CVE-2026-436302026-08-06See advisory
Criticalllama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata() function computes write size without overflow checking, allowing attackers with write access to…CVE-2026-436292026-08-06See advisory
Highllama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with…CVE-2026-436282026-08-06See advisory
Highllama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes.CVE-2026-436272026-08-06See advisory
Highllama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new1batch() allocates memory using malloc() while free1batch() deallocates it using the C++ delete operator, causing heap…CVE-2026-436222026-08-06See advisory
Criticalllama.cpp is an inference of several LLM models in C/C++.CVE-2026-34159 · GHSA-j8rj-fmpv-wcxw2026-04-01b8492
Highllama.cpp is an inference of several LLM models in C/C++.CVE-2026-33298 · GHSA-96jg-mvhq-q7q72026-03-24b7824
Highllama.cpp is an inference of several LLM models in C/C++.CVE-2026-27940 · GHSA-3p4r-fq3f-q74v2026-03-12b8146
Highllama.cpp is an inference of several LLM models in C/C++.CVE-2026-21869 · GHSA-8947-pfff-2f3c2026-01-08See advisory
HighInteger Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in ggufCVE-2025-53630 · GHSA-vgg9-87g3-85w82025-07-10See advisory
MediumHeap-based Buffer Over-read in llamamodelloadGHSA-g4cc-763q-h9h62025-06-25See advisory
Highllama.cpp is an inference of several LLM models in C/C++.CVE-2025-52566 · GHSA-7rxv-5jhh-j6xx2025-06-24b5721
Highllama.cpp is an inference of several LLM models in C/C++.CVE-2025-49847 · GHSA-8wwf-w4qm-gpqr2025-06-17b5662
Criticalllama.cpp provides LLM inference in C/C++.CVE-2024-42479 · GHSA-wcr5-566p-9cwj2024-08-12b3561
Mediumllama.cpp provides LLM inference in C/C++.CVE-2024-42478 · GHSA-5vm9-p64x-gqw92024-08-12b3561
Mediumllama.cpp provides LLM inference in C/C++.CVE-2024-42477 · GHSA-mqp6-7pv6-fqjf2024-08-12b3561
Mediumllama.cpp provides LLM inference in C/C++.CVE-2024-41130 · GHSA-49q7-2jmh-92fp2024-07-22b3427
HighLlama.cpp is LLM inference in C/C++.CVE-2024-32878 · GHSA-p5mv-gjc5-mwqv2024-04-26b2740
HighA heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality of llama.cpp Commit 18c2e17.CVE-2024-236052024-02-262024-01-09
HighA heap-based buffer overflow vulnerability exists in the GGUF library gguffreadstr functionality of llama.cpp Commit 18c2e17.CVE-2024-234962024-02-262024-01-09
HighA heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17.CVE-2024-218362024-02-262024-01-09
HighA heap-based buffer overflow vulnerability exists in the GGUF library GGUFTYPEARRAY/GGUFTYPESTRING parsing functionality of llama.cpp Commit 18c2e17.CVE-2024-218252024-02-262024-01-09
HighA heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality of llama.cpp Commit 18c2e17.CVE-2024-218022024-02-262024-01-09

CVEs matched by the NVD's product names and advisories published in the product's own repository, checked 2026-11-18. Where the vendor runs the service, its fix reaches you without an update.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].

This product uses the NVD API but is not endorsed or certified by the NVD. Product facts from github.com, checked 2026-11-18. Logos are their owners' marks, shown only to identify the products.