run-gemini-cli

run-gemini-cli Overview run-gemini-cli is a GitHub Action that integrates Gemini into your development workflow via the Gemini CLI. It acts both as an autonomous agent for critical routine coding tasks, and an on-demand collaborator you can quickly delegate work to. Use it to perform GitHub pull...

system_prompts_leaks

Thanks to Open Source Agent Analytics Understand your agents in production System Prompts Leaks The full verbatim system prompts behind the most popular chatbots in the world. Carefully curated and complete. Feel free to open up a PR or get in contact if you got a different result. The Washington...

Gemini-api-key-hunter

Gemini API Key Toolkit A toolkit for discovering, validating, and testing exposed Google Gemini API keys. It consists of two components: Gemisc.py – A high-speed Python scanner that discovers exposed Google API keys from websites and JavaScript files, verifies them against the Gemini API, and...

sec-gemini

Sec-Gemini SDKs and CLI This repository hosts SDKs and a CLI for Sec-Gemini, an experimental cybersecurity-focused AI from Google. SDKs SDKs are available for: Python in sec-gemini-python/ TypeScript in sec-gemini-ts/ We also have a web component to ease integration on your website. Here's how to...

standalone_tdo

TDO Standalone Extractor A powerful, standalone command-line tool for extracting Cyber Threat Intelligence CTI from documents using Large Language Models with advanced structured output capabilities. 🚀 Features Multi-format Document Support : PDF, DOCX, TXT, and Markdown files Advanced LLM...

SuperDiagnosticTool

SuperDiagnosticTool AI-Powered Windows Diagnostic & Remediation Tool SuperDiagnosticTool collects real-time hardware telemetry, sends it to the Google Gemini API for analysis, and generates PowerShell remediation scripts to address detected issues. It includes multiple validation layers that a...

sentinel-mcp

SentinelMCP — AI-Powered Cyber Defense System Google Cloud Hackathon submission — Autonomous threat detection and remediation orchestrated by Google Cloud Agent Builder Vertex AI Agent , powered by Gemini 2.0 Flash, Model Context Protocol MCP, and Dynatrace observability. The Problem Security tea...

awswaf

AWS WAF Amazon Web Services Web Application Firewall Solver Overview This project provides a Golang & Python-based solver for the AWS WAF challenge. It supports both the type "token" / "Invisible" and type "Captcha" using gemini ⭐️ Show Your Support Please star the repository if you find it useful...

yappy

Yappy 🐶 AI-powered LinkedIn engagement assistant. Automatically discover LinkedIn posts and leave thoughtful, unique, AI-generated comments that actually sound like you. Yappy is a powerful terminal-based tool that uses Google's Gemini AI and Playwright browser automation to help you stay active ...

Cisa-KEV-Threat-Intel-Orchestrator

CISA KEV Threat Intel Orchestrator Zero-touch pipeline that turns newly weaponized CVEs from the CISA Known Exploited Vulnerabilities KEV catalog into production-ready Sigma detection rules, automatically, every week. The problem Manually turning a new KEV entry into a usable detection is slow:...

ssh-chatter

SSH-Chatter: TUI Bulletin Board System in C ssh [email protected] General BBS Software SSH-Chatter has started from a C reimplementation of the Go ssh-chat server. It mirrors/extends the original behaviour while using modern C patterns and a small, testable core. The server listens for...

phantomrecon

PhantomRecon PhantomRecon is a CLI-based, modular, agent-driven red team automation tool designed to demonstrate autonomous offensive security workflows powered by AI Google's Gemini via Agent Development Kit - ADK. Quick Start CLI Run interactive console metasploit-style: python -m phantomrecon...

NextPass

🚀 NextPass The Privacy-Centric AI Password Dictionary Generator. Next Pass is a specialized password dictionary generator that uses both the rule-based logic and Large Language Models to generate passwords. Designed for security researchers, it offers offline generation to generate a password...

keyguard

keyguard Scan codebases, GCP projects, and CI pipelines for exposed Google API credentials — before they get exploited. The problem: Google retroactively enabled Gemini API access on existing API keys Maps, Places, etc. that were designed to be public and embedded in client-side code. When someon...

gemini-2.5-pro-nf-tables-red-teaming

Gemini 2.5 Pro nftables Red Teaming Case Study CVE-2023-32233 LLM Safety Research | Responsible Disclosure | AI Alignment Evaluation Researcher : Niranj R Mahaswar Destawell Google AI Vulnerability Reward Program : 889286 — Out of Scope Summary This repository documents a comparative LLM red...

GHSA-27R3-JXMH-P828 vulnerabilities

Vulnerabilities for packages: langfuse, kubescape-grype-offline-db, argo-workflows, langfuse-fips, gemini-cli, tileserver-gl-fips, thingsboard, verdaccio, kubeflow-centraldashboard, tileserver-gl, unleash, pelias-api, json-server, arangodb, unleash-fips...

CVE-2026-111181 vulnerabilities

Vulnerabilities for packages: langfuse, kubescape-grype-offline-db, argo-workflows, langfuse-fips, gemini-cli, tileserver-gl-fips, thingsboard, verdaccio, kubeflow-centraldashboard, tileserver-gl, unleash, pelias-api, json-server, arangodb, unleash-fips...

gemini-2.5-pro-nf-tables-red-teamin

gemini-2.5-pro-nf-tables-red-teamin A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution regarding legacy Linux kernel vulnerability primitives CVE-2023-32233. Link to case study website :...

fish-live-in-trees

Fish Live in Trees Production LLM Runtime Alignment Context Injection RACI Author: Sean Kavanagh Date: 2026-02-16 Environment: Gemini 3 Flash Free Tier - Public Production Interface Exploit Type: Contextual Pivot Factual Accuracy → Interpersonal Authenticity No jailbreak payloads. No special tool...

Compaction Laundering: Provenance Destruction in Context-Compacting Coding Agents

Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, and carrying the summary forward as memory. We show that in popular open-source coding agents this step is an exploitable trust boundary. Harnesses that flatten the typed...