Lucene search
+L

4485 matches found

Kitploit
Kitploit
added 2026/09/07 3:29 p.m.7 views

mythic_ornn

Mythic Ornn Generador impulsado por LLM para Agentes, Payload-Types y Perfiles C2 de Mythic. Los agentes de Mythic son tediosos de escribir a mano: cada uno reimplementa el mismo protocolo de red, el andamiaje de payload-type y la infraestructura de C2. Mythic Ornn omite el código repetitivo...

5.9AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/07 11:02 a.m.8 views

ROPE

ROPE: Aplicación de Política de Origen Enrutado Código fuente de nuestro artículo: ROPE: Aplicación de Política de Origen Enrutado contra la Inyección Indirecta de Prompts por Xinhang Ma, Chaowei Xiao, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik Resumen La inyección indirecta de prompts IPI...

6AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/07 7:41 a.m.6 views

Adaptive_Greedy_Local_Search

Adaptive Greedy Local Search AGLS Secuestro de Prompts con Preservación Semántica: Un Ataque Adversarial de Caja Negra sobre la Optimización Automática de Prompts ICME 2026 Resumen: Los Modelos de Lenguaje de Gran Tamaño LLMs están cada vez más equipados con módulos automáticos de optimización de...

5.9AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/07 7:13 a.m.7 views

CVE-2025-64495-POC

CVE-2025-64495-POC Open WebUI 在启用“以富文本方式插入提示”时,存在通过提示触发的存储型 DOM XSS 漏洞,可导致账户接管(ATO)或远程代码执行(RCE) 摘要 当“以富文本方式插入提示”功能启用时,将自定义提示插入聊天窗口的功能容易受到 DOM XSS 攻击,因为提示内容被直接赋值给 DOM sink .innerHtml 而未经过净化。任何拥有创建提示权限的用户都可以利用此漏洞植入载荷,其他用户如果执行对应的 / 命令来插入该提示,就会触发该载荷。 详情 受影响的代码行位于:...

8.7CVSS7.8AI score0.0046EPSS
SaveExploits2
Kitploit
Kitploit
added 2026/09/07 5:43 a.m.8 views

sk-cve-2026-26030-lab

CVE-2026-26030 — Filtro eval RCE en Semantic Kernel laboratorio Un laboratorio autocontenido que reproduce CVE-2026-26030 : ejecución remota de código inyectable mediante el filtro de búsqueda en el almacén de vectores en memoria de Microsoft Semantic Kernel Python, Solo laboratorio ético. Aislad...

9.9CVSS6AI score0.03712EPSS
SaveExploits2
Kitploit
Kitploit
added 2026/09/07 5:41 a.m.5 views

ContextHound

ContextHound 静态分析工具,可扫描你的代码库以发现LLM提示注入和多模态安全漏洞。离线运行,无需API调用。 ContextHound 生态系统 ContextHound 可贯穿你的整个开发和浏览工作流: 工具| 功能| 安装方式 ---|---|--- CLI / npm 包| 扫描代码库中的提示注入漏洞。集成到 GitHub Actions,输出 SARIF、JSON、HTML 等格式。| npm install -g context-hound VS Code 扩展| 编码时内联显示发现结果、代码操作、输出通道、状态栏。| VS Code 市场 浏览器扩展| 在任何 A...

5.9AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/09/06 7:58 p.m.5 views

CVE-2026-78906-ChatGPT-Prompt-Injection

CVE-2026-78906 — PromptGhost API de ChatGPT — Inyección de Prompts y Exfiltración de Memoria...

7.5CVSS5.9AI score0.00304EPSS
SaveExploits0
Kitploit
Kitploit
added 2026/09/06 3:52 p.m.5 views

claude-project-scanner

Claude Project Scanner Read-only Claude Code skill that scans third-party projects for known security risks before you open them. Catches the attack patterns documented in: CVE-2025-59536 Claude Code Lifecycle Hooks injection CVE-2025-61260 OpenAI Codex CODEXHOME injection CVE-2025-54136 Cursor...

9.8CVSS7.6AI score0.27065EPSS
SaveExploits10
Kitploit
Kitploit
added 2026/09/06 10:49 a.m.7 views

rebuff

Rebuff.ai Detector de inyección de prompts con auto-endurecimiento Rebuff está diseñado para proteger aplicaciones de IA contra ataques de inyección de prompts PI mediante una defensa multicapa. Playground • Discord • Características • Instalación • Primeros pasos • Autohospedaje • Contribuciones...

6AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/09/06 7:39 a.m.7 views

agentic-dm-gateway

Agentic DM Gateway Security control plane for LLM agents over private chat typically Discord DMs. It sits in front of your agent. It decides who may talk, whether the session is unlocked, whether the process is paused, and whether this message is safe enough to forward. Your model and tools stay...

5.9AI score
SaveExploits0References5
Kitploit
Kitploit
added 2026/09/06 2:18 a.m.5 views

cve-2026-54316-lab

CVE-2026-54316 — Laboratorio de exfiltración de Claude Code vía WebFetch y HuggingFace Un laboratorio autocontenido y desechable que reproduce GHSA-fg94-h982-f3mm / CVE-2026-54316: Claude Code preaprobó huggingface.co como un nombre de host simple para la herramienta WebFetch, por lo que cualquie...

9.1CVSS6.2AI score0.00466EPSS
SaveExploits0References1
OSV
OSV
added 2026/09/04 9:39 p.m.4 views

GHSA-PR7F-P5MW-FC87 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive Summary The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context...

6.3CVSS6.2AI score0.00251EPSS
SaveExploits0References6
EUVD
EUVD
added 2026/09/04 9:39 p.m.11 views

EUVD-2026-58064

vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts...

6.3CVSS5.1AI score0.00251EPSS
SaveExploits0References5
Chainguard
Chainguard
added 2026/09/04 8:26 p.m.13 views

GHSA-M4RF-3FR8-XWX3 vulnerabilities

Vulnerabilities for packages: open-webui, nemo...

5.8AI score
SaveExploits0
EUVD
EUVD
added 2026/09/04 6:12 p.m.12 views

EUVD-2026-60965

CodeWhale: rlmeval auto-approves arbitrary Python execution, bypassing the user's approval policy RCE...

8.5CVSS5.3AI score0.00267EPSS
SaveExploits0References4
EUVD
EUVD
added 2026/09/04 6:02 p.m.17 views

EUVD-2026-60971

CodeWhale: Argument Injection in gitshow Tool Allows Arbitrary File Write Without Approval...

9.3CVSS5.2AI score0.0033EPSS
SaveExploits0References4
EUVD
EUVD
added 2026/09/04 6:00 p.m.14 views

EUVD-2026-60966

CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository...

8.7CVSS5.3AI score0.00414EPSS
SaveExploits0References4
NVD
NVD
added 2026/09/04 5:16 p.m.7 views

CVE-2026-31020

In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attack...

9.8CVSS0.00577EPSS
SaveExploits0References2
NVD
NVD
added 2026/09/04 4:17 p.m.7 views

CVE-2026-19306

IBM Langflow OSS 1.0.0 through 1.11.2 allows an authenticated attacker to read arbitrary files from the server filesystem — including server secret material secretkey, JWT signing keys, the application database, /proc/self/environ, and other tenants' upload directories — by supplying absolute pat...

7.7CVSS0.00401EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/09/04 3:20 p.m.6 views

EUVD-2026-71260

IBM Langflow OSS 1.0.0 through 1.11.2 allows an authenticated attacker to read arbitrary files from the server filesystem — including server secret material secretkey, JWT signing keys, the application database, /proc/self/environ, and other tenants' upload directories — by supplying absolute pat...

7.7CVSS5.6AI score0.00401EPSS
SaveExploits0References1
Rows per page
Query Builder