Lucene search
+L

5395 matches found

Kitploit
Kitploit
•added 2026/10/05 7:14 a.m.•20 views

CVE-2025-64495-POC

CVE-2025-64495-POC Open WebUI es vulnerable a DOM XSS almacenado a través de prompts cuando 'Insertar Prompt como Texto Enriquecido' está habilitado, resultando en ATO/RCE Resumen La funcionalidad que inserta prompts personalizados en la ventana de chat es vulnerable a DOM XSS cuando 'Insertar...

8.7CVSS8.1AI score0.0046EPSS
SaveExploits2
Kitploit
Kitploit
•added 2026/10/05 5:44 a.m.•13 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...

9.9CVSS6.4AI score0.03784EPSS
SaveExploits2
Kitploit
Kitploit
•added 2026/10/05 5:24 a.m.•12 views

batch_jailbreak

Repositorio oficial de Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim Korea Advanced Institute of Science and Technology KAIST Noticias 2026.09 ¡Nuestro artículo ha sido aceptado en AACL-IJCNLP 2026 Main! 🎉...

6.3AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/05 2:49 a.m.•11 views

ContextHound

ContextHound Herramienta de análisis estático que escanea tu base de código en busca de vulnerabilidades de inyección de prompts en LLM y de seguridad multimodal. Se ejecuta sin conexión, no requiere llamadas a API. El ecosistema ContextHound ContextHound está disponible en todo tu flujo de traba...

6.3AI score
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/10/05 12:00 a.m.•8 views

PT-2026-106004

The convert playwright script prompt in the k6 MCP server accepts a file path as its playwright script argument. Paths given in the documented '@'-prefixed form are restricted to the server's current working directory, but a bare path is resolved by a separate undocumented code path that applies ...

6.5CVSS5.8AI score0.00379EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/10/05 12:00 a.m.•8 views

PT-2026-106262

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.30.0 Description In vLLM, Harmony tool continuations submitted through the "POST /v1/responses" endpoint rebuild the next-turn engine input without preserving the cache salt value. This causes the continuation prefix t...

3.1CVSS5.7AI score0.00216EPSS
SaveExploits0References8
Packet Storm News
Packet Storm News
•added 2026/10/05 12:00 a.m.•6 views

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/05 12:00 a.m.•7 views

Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...

5.9AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/10/04 10:58 p.m.•20 views

mythic_ornn

Mythic Ornn LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles. Mythic agents are tedious to write by hand: every one re-implements the same wire protocol, payload-type scaffolding, and C2 plumbing. Mythic Ornn skips the boilerplate by turning the official Mythic developer docs...

6.1AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/04 8:15 p.m.•31 views

CVE-2026-24055-OAuth-Langfuse

CVE-2026-24055 — Instalación de Slack OAuth sin autenticación en Langfuse Proyecto del curso Seguridad Web y de Aplicaciones — Grupo 06, clase NT213.Q21.ANTT 📌 Resumen El proyecto reproduce una vulnerabilidad de seguridad real ya publicada CVE-2026-24055 en la plataforma Langfuse — un endpoint...

6.3CVSS6.2AI score0.00442EPSS
SaveExploits2References2
Kitploit
Kitploit
•added 2026/10/04 7:59 p.m.•8 views

CVE-2026-78906-ChatGPT-Prompt-Injection

CVE-2026-78906 — PromptGhost API de ChatGPT — Inyección de Prompts y Exfiltración de Memoria Campo| Valor ---|--- Severidad| 8.7 Alta Vector| Red Versiones Afectadas| API v1.0 – v1.3 Descubierto Por| 𝕍𝕠𝕤𝕤🥷 Descripción Una vulnerabilidad crítica en la API de ChatGPT de OpenAI permite a un atacante...

7.5CVSS7.6AI score0.00415EPSS
SaveExploits0
Kitploit
Kitploit
•added 2026/10/04 3:52 p.m.•17 views

claude-project-scanner

Escáner de Proyectos Claude Skill de Claude Code de solo lectura que escanea proyectos de terceros en busca de riesgos de seguridad conocidos antes de que los abras. Detecta los patrones de ataque documentados en: CVE-2025-59536 inyección de Lifecycle Hooks de Claude Code CVE-2025-61260 inyección...

9.8CVSS7.9AI score0.28255EPSS
SaveExploits10
Kitploit
Kitploit
•added 2026/10/04 10:50 a.m.•10 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...

6.2AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/10/04 7:40 a.m.•17 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...

6.1AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/10/04 2:51 a.m.•11 views

prompt-injection-email-samples

Prompt-Injection Email Samples A small, open test set of emails for checking whether your email security controls and AI mailbox assistants handle indirect prompt injection : instructions hidden in an email that try to hijack an AI assistant when it reads, summarizes or acts on that email. The se...

6AI score
SaveExploits0References12
Kitploit
Kitploit
•added 2026/10/04 2:19 a.m.•15 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...

9.1CVSS6.4AI score0.0052EPSS
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/04 12:49 a.m.•12 views

llm-prompt-injection-resources

llm-prompt-injection-resources Una colección seleccionada de recursos para aprender e investigar sobre ataques de inyección de prompts en LLM, defensas y seguridad. Donar Apoya el mantenimiento de este proyecto con PayPal o escaneando el código QR a continuación...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/04 12:00 a.m.•4 views

Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection

Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged prompt injection. We...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/04 12:00 a.m.•8 views

Can CaMeLs Talk? Securing Multi-Agent Systems against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL Debenedetti et al., 2025 mitigates this threat for an individual agent by separating trusted control flow from...

5.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/04 12:00 a.m.•8 views

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implicatio...

5.9AI score
SaveExploits0
Rows per page
Query Builder