Search vulnerabilities

Use the Query Builder to create your own search query, or check out the documentation to learn the search syntax.

Results 34

Export CSV
CVE-2026-70639

llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp

llama.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. Attackers can supply a malicious, corrupt, or truncated model file to trigger a null context condition, causing a SIGSEGV crash that terminates the Android application process and results in denial of service.

CVSS 4.0 · 6.8 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-70638

llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp

llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without overflow validation, causing heap buffer allocation to wrap and allocate insufficient memory. Attackers can exploit this by providing a crafted n_seq_max value through a malicious model file or JNI call to trigger heap corruption and achieve denial of service or arbitrary code execution on Android applications using the LLaMA-Android binding.

CVSS 4.0 · 8.5 High EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43632

llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints

llama.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/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.

CVSS 4.0 · 9.2 Critical EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43631

llama.cpp b7492–b9060 Use-After-Free RCE via llama-server

llama.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 code. Attackers can trigger the vulnerability by sending requests to affected endpoints while the server transitions to sleep mode, causing concurrent worker threads to dereference a freed vocab pointer that can be reclaimed with attacker-controlled data to achieve remote code execution.

CVSS 4.0 · 9.2 Critical EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43629

llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.

CVSS 4.0 · 9.2 Critical EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43628

llama.cpp b3978–b9058 Integer Underflow via DRY Sampler

llama.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 dry_allowed_length set to INT32_MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.

CVSS 4.0 · 8.5 High EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43627

llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causing heap corruption and potentially achieving arbitrary code execution through subsequent batch operations that write past allocated buffer boundaries.

CVSS 4.0 · 8.5 High EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-43622

llama.cpp b1886–b7445 Double Free via llama-android.cpp

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.

CVSS 4.0 · 8.5 High EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-18581

ggml-org llama.cpp Jinja Minja Template parser.cpp assertion

A vulnerability was determined in ggml-org llama.cpp e15efe0. Affected by this issue is some unknown functionality of the file common/jinja/parser.cpp of the component Jinja Minja Template Parser. Executing a manipulation with the input {{9|9|{ can lead to reachable assertion. The attack requires local access. The exploit has been publicly disclosed and may be utilized. The project was informed of the problem early through an issue report but has not responded yet.

CVSS 4.0 · 4.8 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml-org
Products
Llama.cpp
CVE-2026-17501

ggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursion

A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes uncontrolled recursion. The attack may be initiated remotely. The pull request to fix this issue awaits acceptance.

CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Llama.cpp Llama.cpp
CVE-2026-17500

ggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereference

A vulnerability was detected in ggml-org llama.cpp d006858/e15efe0. This affects the function _visit_pattern of the file common/json-schema-to-grammar.cpp. The manipulation results in null pointer dereference. The attack can be launched remotely. The pull request to fix this issue awaits acceptance.

CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml-org
Products
Llama.cpp
CVE-2026-17513

ggml-org whisper.cpp ggml.c ggml_ftype_to_ggml_type assertion

A vulnerability was found in ggml-org whisper.cpp 95ea8f9b. Affected is the function ggml_ftype_to_ggml_type of the file ggml/src/ggml.c. The manipulation of the argument ftype results in reachable assertion. The attack requires a local approach. The project was informed of the problem early through an issue report but has not responded yet.

CVSS 4.0 · 4.8 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml-org
Products
Whisper.cpp
CVE-2026-17512

ggml-org whisper.cpp log_mel_spectrogram out-of-bounds

A vulnerability has been found in ggml-org whisper.cpp 1.8.4-58. This impacts the function log_mel_spectrogram of the file src/whisper.cpp. The manipulation leads to out-of-bounds read. The attack needs to be performed locally. The pull request to fix this issue awaits acceptance.

CVSS 4.0 · 4.8 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml-org
Products
Whisper.cpp
CVE-2026-10298

ggml-org whisper.cpp ggml.c whisper_model_load null pointer dereference

A security flaw has been discovered in ggml-org whisper.cpp up to 1.8.2. This vulnerability affects the function whisper_model_load of the file ggml/src/ggml.c. The manipulation results in null pointer dereference. Attacking locally is a requirement. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

CVSS 4.0 · 4.8 Medium EPSS < 1% KEV · Not listed
Vendors
Ggml Ggml-org
Products
Whisper.cpp Whisper.cpp