ggml llama.cpp是ggml组织开源的一个纯C/C++语言模型推理工具。 ggml llama.cpp e15efe0版本存在资源管理错误漏洞,该漏洞源于JSON-Schema-to-GBNF Conversion组件中transform函数的资源分配问题,可能导致远程攻击者造成拒绝服务。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-17500 | 5.3 MEDIUM | ggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereference |
| CVE-2026-17512 | 3.3 LOW | ggml-org whisper.cpp log_mel_spectrogram out-of-bounds |
| CVE-2026-17513 | 3.3 LOW | ggml-org whisper.cpp ggml.c ggml_ftype_to_ggml_type assertion |
No comments yet