open-source-llm-scanners

open-source-llm-scanners A list of open source LLM security scanners on GitHub, ordered by Stars. It does not provide in-depth analysis. A minimum of 10 stars are needed as a low bar 😁 Related: open-source-web-scanners LLM Scanners Tools which can find a range of vulnerabilities in LLM...

tealtiger

TealTiger AI Agent Security & Governance SDK Deterministic governance, guardrails, cost tracking, and policy management for LLM applications. Open source. TypeScript + Python. Works with any provider. Website · Documentation · Examples · Discord · Contributing ⚡ 60-second quickstart Install: npm...

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...

LLMMap

LLMMap LLMMap is an automated prompt injection testing framework for LLM-integrated applications. It discovers injection points in HTTP requests, generates targeted attack prompts using a dual-LLM architecture, fires them at the target, and confirms findings with statistical reliability testing...

promptmap

O O o.-. Humans, Do Not Resist! |/ ,-'-. / /, / /|.-.| / --O-- .--""" /\ /\ | o.o / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /||| ./|||,| .// / / |-----| || || || || promptmap2 是一个用于自定义 LLM 应用的自动化提示注入扫描器。它支持两种测试模式： 白盒测试：...

aegis-latent-core

Aegis Latent Core Puerta de enlace de gobernanza de IA y evidencia criptográfica Aegis Latent Core registra evidencia firmada y vinculada por hash de cada llamada de IA gobernada — antes de que la respuesta llegue al solicitante — y emite una prueba portátil que un tercero verifica sin confiar en...

CVE-2025-3248

CVE-2025-3248 — Langflow RCE Exploit Remote Code Execution RCE exploit for Langflow applications vulnerable to CVE-2025-3248. Affected Endpoint: /api/v1/validate/code 🚀 Exploit Features 🔓 Remote & unauthenticated RCE 🔐 No authentication required 🐍 Python3 one-liner script 🎨 Colorized terminal...

The OWASP LLM Top 10 Was the Warm-Up: What Comes Next

This is Post 3 of a four-part series: Post 1: Agentic AI Security: The Chatbot Era Is Over Post 2: Generative AI Security: Why AI Needs a New Kind of Security Post 4: OWASP LLM Top 10 2026: Every Move Points the Same Direction When the OWASP Top 10 for LLM Applications arrived, it did the industr...

The OWASP Top 10 for LLM Applications 2026: From Model Risks to Agentic Security

...

Flowise 安全漏洞

Flowise is a FlowiseAI open source tool for easily building LLM applications. A security vulnerability exists in Flowise versions prior to 3.0.5 that stems from an unfiltered IFRAME element and could lead to a cross-site scripting attack...

EUVD-2024-2367

Malicious code in bioql PyPI...

Wallarm Research Releases Nuclei Template to Counter Threats Targeting LLM Apps

Wallarm Research has just released a powerful new Nuclei template targeting a new kind of exposure: the Model Context Protocol MCP. This isn’t about legacy devtools or generic JSON-RPC pinging. It’s about the protocol fueling next-gen LLM applications — and it’s already showing up exposed in the...