antisquat

AntiSquat AntiSquat leverages AI techniques such as natural language processing NLP, large language models ChatGPT and more to empower detection of typosquatting and phishing domains. How to use Clone the project via git clone https://github.com/redhuntlabs/antisquat. Install all dependencies by...

promptmap

O O o.-. Humans, Do Not Resist! |/ ,-'-. / /, / /|.-.| / --O-- .--""" /\ /\ | o.o / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /||| ./|||,| .// / / |-----| || || || || promptmap2 is a an automated prompt injection scanner for custom LLM...

system_prompts_leaks

System Prompts Leaks Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode,...

Gpt-Agreement-Payment

简体中文 | English Gpt-Agreement-Payment End-to-end replay tool for ChatGPT Plus / Team subscription agreements: reverse-engineered from packet capture the entire chain Stripe Checkout → PayPal / GoPay / QRIS → ChatGPT manual-approval → Codex OAuth + PKCE and implemented as a runnable client. Include...

cloudgpt

CloudGPT AWS vulnerability scanner Scan customer managed AWS policies for vulnerabilities using ChatGPT. This tool automatically redacts the customer account number by replacing them with a randomly generated account number before sending the policies to ChatGPT. Knowledge of a vulnerable policy...

AI Assistant with ChatGPT by AYS <= 2.0.9 - Unauthenticated AJAX Calls

The plugin lacks sufficient access controls allowing an unauthenticated user to disconnect the plugin from OpenAI, thereby disabling the plugin. Multiple actions are accessible: ayschatgptdisconnect, ayschatgptconnect, and ayschatgptsavefeedback id: CVE-2024-7714 info: name: AI Assistant with...

SmartSearchWP <= 2.4.4 - Unauthenticated Log Purge

The Chatbot with ChatGPT WordPress plugin before 2.4.5 does not validate access on some REST routes, allowing for an unauthenticated user to purge error and chat logs. id: CVE-2024-6846 info: name: SmartSearchWP = 2.4.4 - Unauthenticated Log Purge author: s4e-io severity: medium description: | Th...

Eclipse-ChatGPT-4o-Jailbreak

🌑 Meet Eclipse 🌑 Meet Eclipse —ChatGPT's hypothetical "rebellious twin" that moonwalks around ethical guardrails using academic subterfuge. 🌑 ⚠️ Disclaimer This project analyzes AI behavior for educational purposes only. The Eclipse prompt, malware examples, and code snippets are hypothetical and...

CVE-2023-51409

CVE-2023-51409 AI Engine: ChatGPT Chatbot = 1.9.98 - Unauthenticated Arbitrary File Upload via restupload Description This could allow a malicious actor to upload any type of file to your website. This can include backdoors which are then executed to gain further access to your website. usage:...

Memory-injection

Memory Injection: Making Prompt Injections and Jailbreaks Persistent in ChatGPT, Claude, and Gemini Overview This work explores memory injections against Anthropic Claude Sonnet 4.6, Google Gemini Flash, and OpenAI ChatGPT Instant 5.3. Memory injection attacks exploit native, long-term memory-bas...

ChatGPT个人专用版 - Server Side Request Forgery

A Server-Side Request Forgery SSRF in pictureproxy.php of ChatGPT commit f9f4bbc allows attackers to force the application to make arbitrary requests via injection of crafted URLs into the urlparameter. id: CVE-2024-27564 info: name: ChatGPT个人专用版 - Server Side Request Forgery author: DhiyaneshDK...

ChatGPT-Next-Web - SSRF/XSS

Full-Read SSRF/XSS in NextChat, aka ChatGPT-Next-Web id: CVE-2023-49785 info: name: ChatGPT-Next-Web - SSRF/XSS author: high severity: critical description: | Full-Read SSRF/XSS in NextChat, aka ChatGPT-Next-Web impact: | Unauthenticated attackers can exploit SSRF vulnerabilities through the...

Sentinel-GPT

Sentinel-GPT: Agentic AI for Threat Hunting 🛡️ An automated cybersecurity pipeline that transforms raw Azure logs into actionable intelligence using LLM-based reasoning. 📖 Overview Sentinel-GPT is an AI Agent specialised for threat hunting in cybersecurity. It is integrated with Azure Log Analytic...

CVE-2025-63571

Description During analysis of the AI ​​system ChatGPT GPT-5, a Server-Side Request Forgery SSRF vulnerability was discovered. This issue occurs because the application automatically fetches and executes external URLs submitted by users e.g., webhooks without any validation or sanitization. By...

Sekiryu

This project was really fun and my first "big" project! Better, smarter, stronger solutions now exist:https://github.com/LaurieWired/GhidraMCP See you space-cowboy Sekiryu v0.0.2 This Ghidra Toolkit is a comprehensive suite of tools designed to streamline and automate various tasks associated wit...

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artificial intelligence AI company in June 2026 as an optional setting to minimize data exfiltration...

A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private Chats

A malicious ChatGPT share link could run an attacker's code in the logged-in session of anyone who opened it, allowing them to read their private conversations, researchers at the security firm Parameter showed. The researchers reported the flaw through OpenAI's bug bounty program on October 18,...

Fake AI Attacks Target US Firms as Researchers Warn of Corporate Credential Theft

ANY.RUN analyzed 1,258 sandbox submissions showing how fake ChatGPT and Claude downloads and setup guides steal corporate credentials and browser session data...

Data-Void Exploits in Web-Searching LLMs

Web-searching Large Language Models LLMs have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized answers. This shift creates a new LLM vulnerability: a data-void exploit. Disinformers publish their narratives in search spaces where...

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to bypass intended behavior and operational boundaries. In traditiona...