
AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Curated collection of extracted system prompts from major AI chatbots including Claude, ChatGPT, Gemini, Grok, and Copilot. Updated regularly with…

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power…

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Technical analysis and detection guidance for CVE-2026-21589, a pre-auth path traversal arbitrary file access flaw in Atlassian Data Center products.

AIL framework - Analysis Information Leak framework. Project moved to https://github.com/ail-project

This project hosts security advisories and their accompanying proof-of-concepts related to research conducted at Google which impact non-Google owned…

Fully automatic censorship removal for language models

Repository created to share information about tactics, techniques and procedures used by threat actors. Initially with ransomware groups and evolving…

Coordination structure for AI security standards and guidelines, reducing fragmentation and providing clear guidance for securing AI systems across…

https://cve.mitre.org/

😱 A curated list of amazingly awesome OSINT

The Ultimate CVE Proof of Concept (PoC) & Exploit Database. A zero-API, high-performance aggregator for 0days, vulnerabilities, and Threat…

Tracking interesting Linux (and UNIX) malware. Send PRs

Proof-of-concept and research material for CVE-2026-59265, a LibreOffice and OpenOffice vulnerability, intended for authorized lab testing and…

Python detection artifact that checks Atlassian Jira, Confluence, and Bitbucket instances for the CVE-2026-21589 arbitrary file read vulnerability.

Independent offline protocol-boundary regressions for published urllib3 fixes, with pinned releases and upstream attribution.

Reference resources for Google's vulnerability reward programs, including domain tiers, OSS repository tier lists, and rewarded patch examples for…