SUSE CVE-2026-52132

llama.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...

DEBIAN-CVE-2026-52132

llama.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...

UBUNTU-CVE-2026-52132

llama.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-2026-52132

llama.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...

PT-2026-84371

Name of the Vulnerable Software and Affected Versions llama.cpp versions prior to commit 97f06e9 Description When started with the --reranking flag, the software is susceptible to a denial of service. A remote attacker can trigger a std::bad alloc a memory allocation failure and an HTTP 500 error...

CVE-2026-52132

llama.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...

EUVD-2026-69410

llama.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-2026-52132

llama.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...

PT-2026-41192

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.9.5 Description An information disclosure issue exists where the 'GET /api/v1/retrieval/' endpoint returns live RAG Retrieval-Augmented Generation pipeline configuration to any unauthenticated HTTP client. No...

Arbitrary Code Injection

Overview sglang is a SGLang is a fast serving framework for large language models and vision language models. Affected versions of this package are vulnerable to Arbitrary Code Injection via the reranking endpoint when a model file containing a malicious tokenizer.chattemplate is loaded, due to...

EUVD-2026-23860

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

CVE-2026-5760

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

CVE-2026-5760 CVE-2026-5760

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

CVE-2026-5760

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

CVE-2026-5760

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

CVE-2026-5760: Improper Control of Generation of Code

SGLang's reranking endpoint /v1/rerank achieves Remote Code Execution RCE when a model file containing a malcious tokenizer.chattemplate is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment...

ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis

Modern networks generate vast, heterogeneous traffic that must be continuously analyzed for security and performance. Traditional network traffic analysis systems, whether rule-based or machine learning-driven, often suffer from high false positives and lack interpretability, limiting analyst...

Are LLMs Reliable Rankers? Rank Manipulation Via Two-Stage Token Optimization

Large language models LLMs are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First RAF, a two-stage token optimization method that crafts concise textual...