Advisories · Technology
ggml-org llama.cpp.
Every CVE that names ggml-org llama.cpp among its affected products, newest first. Vendors and products are as the CNA wrote them; check the affected versions on each record.
- CVSS 8.7 High
llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Length
- ggml-org llama.cpp
- CWE-248
- CVSS 9.2 CriticalCritical · CVSS 9+
llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv()
- ggml-org llama.cpp
- Memory corruption
- CVSS 6.9 Medium
llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader
- ggml-org llama.cpp
- Memory corruption
- CVSS 6.9 Medium
llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.5 High
llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer
- ggml-org llama.cpp
- CWE-129
- CVSS 6.8 Medium
llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.8 High
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
- ggml-org llama.cpp
- CWE-129
- CVSS 6.9 Medium
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
- ggml-org llama.cpp
- Memory corruption
- CVSS 6.9 Medium
ggml-org llama.cpp Mirostat Sampler llama-sampler.cpp assertion
- ggml-org llama.cpp
- Denial of service
- CVSS 4.8 Medium
ggml-org llama.cpp Pocket-TTS pockettts-gen.cpp list_pockettts_state_slots out-of-bounds write
- ggml-org llama.cpp
- Memory corruption
- CVSS 9.2 CriticalCritical · CVSS 9+
llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser
- ggml-org llama.cpp
- Memory corruption
- CVSS 6.9 Medium
ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertion
- ggml-org llama.cpp
- Denial of service
- CVSS 6.9 Medium
ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_compute null pointer dereference
- ggml-org llama.cpp
- Denial of service
- Memory corruption
- CVSS 6.9 Medium
ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp deserialize_tensor deserialization
- ggml-org llama.cpp
- Insecure deserialization
- CWE-20
- CVSS 9.2 CriticalCritical · CVSS 9+
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
- ggml-org llama.cpp
- Race condition
- Memory corruption
- CVSS 9.2 CriticalCritical · CVSS 9+
llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
- ggml-org llama.cpp
- Race condition
- Memory corruption
- CVSS 6.3 Medium
llama.cpp b4882-b8487 Out-of-Bounds Read Information Disclosure
- ggml-org llama.cpp
- Memory corruption
- Information disclosure
- CVSS 9.2 CriticalCritical · CVSS 9+
llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.5 High
llama.cpp b3978–b9058 Integer Underflow via DRY Sampler
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.5 High
llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function
- ggml-org llama.cpp
- Memory corruption
- CVSS 7.3 High
llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
- ggml-org llama.cpp
- Race condition
- Memory corruption
- CVSS 6.8 Medium
llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.5 High
llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.5 High
llama.cpp b1886–b7445 Double Free via llama-android.cpp
- ggml-org llama.cpp
- Memory corruption
- CWE-762
- CVSS 4.8 Medium
ggml-org llama.cpp Jinja Minja Template parser.cpp assertion
- ggml-org llama.cpp
- Denial of service
- CVSS 6.9 Medium
ggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursion
- ggml-org llama.cpp
- Denial of service
- CVSS 6.9 Medium
ggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereference
- ggml-org llama.cpp
- Denial of service
- Memory corruption
- CVSS 9.8 CriticalCritical · CVSS 9+
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
- ggml-org llama.cpp
- Memory corruption
- CVSS 7.8 High
llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
- ggml-org llama.cpp
- Memory corruption
- CVSS 7.8 High
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
- ggml-org llama.cpp
- Memory corruption
- CVSS 4.8 Medium
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.8 High
llama.cpp has Out-of-bounds Write in llama-server
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.9 High
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
- ggml-org llama.cpp
- Memory corruption
- CVSS 8.6 High
llama.cpp tokenizer signed vs. unsigned heap overflow
- ggml-org llama.cpp
- Memory corruption
- CWE-195
- CVSS 8.8 High
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
- ggml-org llama.cpp
- Memory corruption
- CWE-195