Lucene search
+L

232 matches found

Kitploit
Kitploit
added 2026/08/27 12:08 a.m.2 views

redthread

RedThread Trova l'exploit. Giudicalo. Abbozza la correzione. Prova cosa è cambiato. RedThread è un framework CLI-first per testare sistemi LLM, validare i fallimenti e trasformare vulnerabilità confermate in candidati di difesa basati su prove. È costruito per team che necessitano di più di una...

5.4AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/26 10:10 p.m.6 views

AzureRedOps

AzureRedOps Ein Schweizer Taschenmesser für Azure / Entra ID Red Teaming. Autor: Mr.Un1k0d3r TrueCyber Inc Version: 0.1 Sprache: Python 3.12+ Überblick AzureRedOps ist ein offensives Security-Toolkit zur Bewertung der Sicherheitslage von Microsoft Entra ID- und Azure -Mandanten. Es fasst die...

5.9AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/26 9:51 p.m.7 views

nox-framework

███╗ ██╗ ██████╗ ██╗ ██╗ ████╗ ██║██╔═══██╗╚██╗██╔╝ ██╔██╗ ██║██║ ██║ ╚███╔╝ ██║╚██╗██║██║ ██║ ██╔██╗ ██║ ╚████║╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝ Framework di Cyber Threat Intelligence Framework OSINT per red teaming, digital forensics e analisi dell'esposizione aziendale. Introduzione...

5.9AI score
SaveExploits0References4
Kitploit
Kitploit
added 2026/08/26 9:27 p.m.3 views

Hacknetics

Hacknetics Hacknetics 🛡️ Proprietario: ice-wzl Contributori: ice-wzl, Jfox32199 Per favore considera di donare: https://buymeacoffee.com/icewzl Descrizione: Il tuo riferimento unico per OSCP e Red Teaming! 🚀 Questo repository contiene una raccolta curata di frammenti di codice, guide, sintassi di...

5.4AI score
SaveExploits0References5
Kitploit
Kitploit
added 2026/08/26 9:05 p.m.2 views

FFM

Freedom Fighting Mode FFM FFM è un'imbracatura di hacking che puoi utilizzare durante la fase di post-sfruttamento di un impegno di red-teaming. L'idea dello strumento è stata derivata da una conferenza del 2007 di @thegrugq. È stato presentato al SSTIC 2018 video e le diapositive di...

5.3AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/08/26 8:28 p.m.4 views

GC2-sheet

GC2 GC2 Google Command and Control è un'applicazione di Command and Control che consente a un attaccante di eseguire comandi sul computer bersaglio utilizzando Google Sheet o Microsoft SharePoint List e di esfiltrare file tramite Google Drive o Microsoft SharePoint Document. Perché Questo progett...

5.3AI score
SaveExploits0References1
Kitploit
Kitploit
added 2026/08/26 5:56 p.m.4 views

Red-Teaming-TTPs

!CAUTION Questo repository contiene fogli di riferimento, note e script relativi al mio apprendimento nella sicurezza informatica, in particolare Red Teaming. Troverai una varietà di risorse che ho raccolto nel corso degli anni, tra cui: Fogli di riferimento : Guide rapide per strumenti e tecnich...

5.5AI score
SaveExploits0References12
Kitploit
Kitploit
added 2026/08/26 5:37 p.m.5 views

afrog

Uno strumento di sicurezza per Bug Bounty, Pentest e Red Teaming English • 中文 Scarica • Wiki • Afrog PoC 规则编写权威指南 Contributori PoC...

5.3AI score
SaveExploits0References6
Kitploit
Kitploit
added 2026/08/26 7:35 a.m.4 views

apimspray

apimspray apimspray è un kit di password spraying per Entra ID specializzato, progettato per ricerche di sicurezza autorizzate e Red Teaming. Utilizza i gateway di Azure API Management APIM come livello proxy distribuito e rotante per l'IP Rotating. Leggi il Post del Blog per maggiori dettagli su...

5.3AI score
SaveExploits0References1
Kitploit
Kitploit
added 2026/08/26 5:57 a.m.2 views

PoshC2

PoshC2 è un framework C2 consapevole dei proxy utilizzato per assistere i penetration tester nelle attività di red teaming, post-exploitation e movimento laterale. PoshC2 è scritto principalmente in Python3 e segue un formato modulare per consentire agli utenti di aggiungere i propri moduli e...

5.4AI score
SaveExploits0
Kitploit
Kitploit
added 2026/08/25 11:25 a.m.4 views

EvilFontTool

EvilFontTool Uno strumento di inganno basato sui font per red teaming, ricerca sulla sicurezza e qualsiasi altra cosa. EvilFontTool nasconde testo leggibile dalla macchina all'interno di un documento che mostra testo completamente diverso a un lettore umano. Lo fa usando Evil Fonts — font che...

5.4AI score
SaveExploits0References3
Kitploit
Kitploit
added 2026/08/24 12:28 p.m.5 views

nuguard

NuGuard Open Source NuGuard is an open source AI application security toolkit. Its goal is to provide the most extensive redteaming and behavioral validation of Agentic AI applications. With NuGuard, AI developers can focus on building their applications while NuGuard continuously tests and...

5.7AI score
SaveExploits0
The Hacker News
The Hacker News
added 2026/07/16 8:42 a.m.25 views

OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol

OpenAI has disclosed details of GPT-Red , an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. "GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt...

6.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/06/11 12:00 a.m.32 views

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Hierarchical multi-agent systems MAS are rapidly being deployed in high-stakes workflows across domains such as finance and software engineering. In these systems, safety and security are inherently distributed across role-specialized agents, significantly expanding the attack surface, particular...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/06/10 12:00 a.m.29 views

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

5.4AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
added 2026/06/04 7:14 p.m.35 views

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

8.8CVSS5.8AI score0.23992EPSS
SaveExploits7
Packet Storm News
Packet Storm News
added 2026/06/04 12:00 a.m.41 views

RedEdit: Agentic Red-Teaming of Image Safety Classifiers Via MCTS-Guided Photo-Editing

Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image editing remains underexplored. Such behaviors are highly prevalent in daily scenarios but difficult to fully reproduce. T...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/06/02 12:00 a.m.17 views

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Recent computer-using-agent CUA red-teaming papers report prompt-injection attack success rates ASR of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still...

5.5AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/06/01 10:12 a.m.115 views

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

6.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/05/17 12:00 a.m.50 views

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response ADR system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol MCP. We identify three persistent challenges in this domain: 1 limited observability -- existing Endpoint...

5.8AI score
SaveExploits0
Rows per page
Query Builder