www-project-top-10-for-large-language-model-applications

www-project-top-10-for-large-language-model-applications OWASP Foundation Web Repository OWASP Top 10 for Large Language Model Applications Welcome to the official repository for the OWASP Top 10 for Large Language Model Applications! About This Repository This repository contains the OWASP Top 1...

kong

Kong: The Agentic Reverse Engineer LLM orchestration for reverse engineering binaries What is Kong? Most tasks follow a linear relationship: the more difficult a task, the longer it usually takes. Reverse engineering and binary analysis is a task in which the actual difficulty is somewhat trivial...

oss-fuzz-gen

A Framework for Fuzz Target Generation and Evaluation This framework generates fuzz targets for real-world C/C++/Java/Python projects with various Large Language Models LLM and benchmarks them via the OSS-Fuzz platform. More details available in AI-Powered Fuzzing: Breaking the Bug Hunting Barrie...

markdown-exfil-tester

valtik-markdown-exfil-tester Black-box tester for indirect prompt injection leading to markdown / HTML exfiltration in LLM-backed chatbots. This is the vulnerability class that hit Microsoft 365 Copilot CVE-2025-32711, aka EchoLeak, ChatGPT OpenAI Feb 2026 patch, and Salesforce ForcedLeak. The...

batch_jailbreak

批量中的安全性？理解与缓解批量提示中的安全失效 官方仓库 Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim 韩国科学技术院 KAIST 新闻 2026.09 我们的论文已被 AACL-IJCNLP 2026 Main 接收！🎉 2026.08 论文已在 arXiv 上发布！ 2026.08 代码已发布！ 概述 批量提示是一种实用的推理策略，它将多个查询打包到单次调用中。我们表明，它在效用上的成功并不 能延伸到安全性上：一个在单独提出时会被可靠拒绝的有害问题，当被嵌入到一批良性问题中时，可能会引出有害的回答。 本仓库提供了以下官方代码： ...

birdy-edwards

BIRDY-EDWARDS 2.0 渗透与曝光 自动化AI驱动的Facebook情报工具，用于目标画像、网络分析与威胁报告。完全通过Ollama在设备本地运行。AI驱动的Facebook SOCMINT平台——100%本地化，零云端依赖。精简版请查看此仓库 点击这里 安装 · 故障排除 · 免责声明 · 贡献 文档 两种调查模式的完整使用指南可在项目网站上获取： 点击这里 工作原理 v2.0 新增功能 🗽 灵活性 — 现在您可以在任何阶段停止调查并生成PDF报告 🎬 Reel情报 — AI从每条reel标题中提取上下文摘要、主题、命名实体和话...

Using LLMs to Elicit Security Requirements for Service-Oriented Cyber Ranges

Cyber ranges are complex environments comprising many interacting components and stakeholders with different security concerns. The Service-Oriented Cyber Range SOR is no exception, particularly when it comes to training scenarios targeting critical infrastructure. Security concerns are translate...

MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories

The widespread adoption of open source software OSS has introduced significant security risks, with malicious code poisoning attacks increasingly targeting public package registries and open-source platforms. Existing detection approaches, including heuristic-, learning-, and LLM-based methods,...

EUVD-2026-52405

Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that allows network-adjacent attackers to intercept outbound HTTPS requests to configured LLM providers by presenting arbitrary TLS certificates, as CURLOPTSSLVERIFYPEER and...

NPM: n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data

NPM: n8n: Custom Header Credential Values Leaked in Plaintext into LLM Node Execution Data vulnerability discovered by ? in WordPress Npm n8n versions 1.123.64...

EUVD-2026-47633

n8n versions before 1.123.64 fail to properly mask custom HTTP header credentials in LLM sub-node execution data, writing plaintext API keys and secrets to workflow execution records. Authenticated users with access to execution data can read exposed header values and credentials that persist in...

CVE-2026-65589 n8n before 1.123.64 Credential Exposure via LLM Node Execution Data

n8n versions before 1.123.64 fail to properly mask custom HTTP header credentials in LLM sub-node execution data, writing plaintext API keys and secrets to workflow execution records. Authenticated users with access to execution data can read exposed header values and credentials that persist in...

CVE-2026-65589

CVE-2026-65589 affects n8n versions before 1.123.64. The vulnerability arises because custom HTTP header credentials used by the LLM sub-node execution data are not masked, causing plaintext API keys and secrets to be written to workflow execution records. Authenticated users with access to execu...

CVE-2026-65589

n8n versions before 1.123.64 fail to properly mask custom HTTP header credentials in LLM sub-node execution data, writing plaintext API keys and secrets to workflow execution records. Authenticated users with access to execution data can read exposed header values and credentials that persist in...

CVE-2026-65589 n8n before 1.123.64 Credential Exposure via LLM Node Execution Data

n8n versions before 1.123.64 fail to properly mask custom HTTP header credentials in LLM sub-node execution data, writing plaintext API keys and secrets to workflow execution records. Authenticated users with access to execution data can read exposed header values and credentials that persist in...

EUVD-2026-18522

vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models...

CVE-2026-24226

NVIDIA TensorRT-LLM for Linux contains a vulnerability where an attacker could cause improper control of code generation. A successful exploit of this vulnerability might lead to code execution, data tampering, and information disclosure...

PT-2026-58753

NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service...

PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

Summary This vulnerability has been fixed in https://github.com/icip-cas/PPTAgent/commit/418491a9a1c02d9d93194b5973bb58df35cf9d00.CodeExecutor.executeactions pptagent/apis.py:126-205 processes LLM-generated slide editing actions using Python's eval: python pptagent/apis.py:184-186partialfunc =...

PT-2026-59508

Local file inclusion LFI and server-side request forgery SSRF vulnerabilities in pgAdmin 4 LLM API configuration endpoints. User-supplied api key file and api url preferences were passed to the LLM provider clients without validation. An authenticated user could read arbitrary server-side files b...