seclab-taskflow-agent

GitHub Security Lab Taskflow Agent The Security Lab Taskflow Agent is an MCP-enabled multi-Agent framework for declarative, YAML-driven agentic workflows. Built on top of the OpenAI Agents SDK, it uses Pydantic for grammar validation and Jinja2 for template rendering. Core Concepts The Taskflow...

EscalateGPT

Introduction IAM Privilege Escalation Identification Tool Features 🛠️ Identifies potential privilege escalation issues in AWS IAM and Azure RBAC policies 💻 Leverages most advanced AI models via OpenAI for analysis 👍 Returns escalation paths and mitigation recommendations in easy to understand JSON...

privacy-parser

Privacy Parser Find every piece of PII in a pile of text and get it back as structured spans. Built on OpenAI Privacy Filter: same 1.5B model, same labels, same weights. Privacy Filter masks. Privacy Parser extracts. Hi Quindle Testwick [email protected] / +1-415-555-0102, account...

codex-security

Codex Security Codex Security helps you find, investigate, and fix vulnerabilities in your code. Use its security workflows in Codex, or automate them with the @openai/codex-security CLI and TypeScript SDK. In Codex: choose a security workflow. In a terminal: install the CLI and scan your...

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 < 2.4.6 - OpenAI Key Disclosure

The plugin does not have proper authorization in one of its REST endpoint, allowing unauthenticated users to retrieve the encoded key and then decode it, thereby leaking the OpenAI API key. id: CVE-2024-6845 info: name: SmartSearchWP 2.4.6 - OpenAI Key Disclosure author: s4e-io severity: medium...

CyberBattleSim

CyberBattleSim April 8th, 2021: See the announcement on the Microsoft Security Blog. CyberBattleSim is an experimentation research platform to investigate the interaction of automated agents operating in a simulated abstract enterprise network environment. The simulation provides a high-level...

burpgpt

!IMPORTANT Announcing the launch of BurpGPT Pro, the edition specifically tailored to meet the needs of professionals and cyber boutiques. Discover a host of powerful features and a user-friendly interface that enhances your capabilities and ensures an optimal user experience. To access these...

CL4R1T4S

CL4R1T4S AI SYSTEMS TRANSPARENCY AND OBSERVABILITY FOR ALL! Full extracted system prompts, guidelines, and tools from OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, Windsurf, Devin, Manus, Replit, and more – virtually all major AI models + agents! 📌 Why This Exists "In order to trust the...

attack-stix-data

ATT&CK® STIX Data MITRE ATT&CK is a globally-accessible knowledge base of adversary tactics and techniques based on real-world observations. The ATT&CK knowledge base is used as a foundation for the development of specific threat models and methodologies in the private sector, in government, and ...

lm-fingerprint

LM-Fingerprint Fingerprints the serving stack behind an OpenAI-compatible chat endpoint. It records tokenizer accounting, hidden template offset, validation prose, JSON/SSE shape, role acceptance, named limits, and gateway headers. It does not load weights, store API keys, or ask the model who it...

GhidrAssist

GhidrAssist Author: Jason Tang An advanced LLM-powered plugin for interactive reverse engineering assistance in Ghidra. Description GhidrAssist integrates Large Language Models LLMs into Ghidra to provide intelligent assistance for binary exploration and reverse engineering. It supports any OpenA...

ReconAIzer

ReconAIzer ReconAIzer is a powerful Jython extension for Burp Suite that leverages OpenAI to help bug bounty hunters optimize their recon process. This extension automates various tasks, making it easier and faster for security researchers to identify and exploit vulnerabilities. Once installed,...

BinAIVulHunter

BinAIVulHunter An IDA PRO plugin to help in finding vulnerabilites in binaries. Use IDA PRO HexRays decompiler with OpenAIChatGPT to find possible vulnerabilities in binaries Disclaimer, possible replies while trying to find binary vulnerabilites using an AI may lead to false positives, however i...

POC_CVE-2024-10829

POCCVE-2024-36420 Local reproduction lab and nuclei template draft for CVE-2024-36420 affecting Flowise. Summary CVE-2024-36420 is an arbitrary file read in Flowise caused by unsanitized use of the fileName body parameter in: POST /api/v1/openai-assistants-file This lab was used to validate:...

ghost-compact

Xint's OpenAI Compaction Research Two major findings in OpenAI's compaction API: GhostCompact : a billing bug that made OpenAI compaction, and the arbitrary inference it can perform, nearly free. Code: ghostcompact.py, ghostscan.py. blog post Compaction Smuggling : steering compaction to copy a...

badger-builder

badger-builder badger-builder is an AI-assisted tool for generating dynamic Brute Ratel C4 profiles. Simply provide badger-builder a flavor for your desired profile and it will prompt OpenAI for fitting configurations. Listener/payload profile configs that are AI generated: C2 URIs Request/respon...

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...

IDA_Plugin_PCodeGPT

PCodeGPT A plugin for ida 7.5 7.x and 8.x. Description This is a gepetto and WPeChatGPT modified IDA plug-in that I use to automate code analysis using OpenAI's GPT 3.5 or GPT-4. Currently, only Chinese is supported. Usage Move PCodeGPT.py into the plugins folder, and the plug-in will be...

POC_CVE-2024-36420

POCCVE-2024-36420 Local reproduction lab and nuclei template draft for CVE-2024-36420 affecting Flowise. Summary CVE-2024-36420 is an arbitrary file read in Flowise caused by unsanitized use of the fileName body parameter in: POST /api/v1/openai-assistants-file This lab was used to validate:...