#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
yingtaoren/d-scanAnalyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.
useaitechdad/openclaw-technical-analysisThis technical research and review is for educational purposes on public code and constitutes Fair Dealing under the Copyright Act (Canada).
ololadeabiola03/aisecplus-week01-servicenow-ai-security-incidentResearch and analysis of the ServiceNow Virtual Agent vulnerability (CVE-2025-12420), including attack flow, MITRE ATT&CK mapping, detection…
imthecopilotnow/cve-2025-492025Detailed security advisory for CVE-2025-492025, documenting a UI misrepresentation vulnerability in Copilot AI that injects unintended hyperlinks…
rootdirective-sec/cve-2026-33626-labDocker Compose lab reproducing CVE-2026-33626 SSRF in LMDeploy's vision-language image loader. Compares vulnerable (0.12.0) and patched (0.12.3)…
sushank05/mcp-doormanA lightweight mcp to prevent poisoning CVE (CVE-2025-54136), researchers hijacking Claude Code/Copilot/Gemini via prompt injection, and hundreds of…
rohitberiwala/claude-code-mcp-injection-pocProfessional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading…
1numak1/cve-2025-31337CVE-2025-31337 Security Advisory - Critical Buffer Overflow in AI Chatbot Framework
holiday-830/llm-council-vaptAI-powered peer review for Pentest findings or Bug Bounty Reports — validates severity, evidence, and reporting quality before delivery using…
dwulf/eternal-codexMy manifesto, and stories, images, and phun stuff
george0papasotiriou/cve-2026-23001-hugging-face-transformers-model-deserialization-arbitrary-code-via-pickle-Proof-of-concept for CVE-2026-23001: demonstrates RCE through unsafe pickle deserialization in Hugging Face Transformers by crafting a malicious…
destawell/gemini-2.5-pro-nf-tables-red-teaminA technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…
balajigund/research-on-cve-2025-9998vulnerability in CVE 2025-9998 and solution for those vulnerability with help artificial intelligence
soemoescode/guardskillRead-only scanner for git settings that let a repository run code in coding agents (Claude Code, Codex, Cursor, Copilot). Covers the GitSpawn class…
kstenerud/yoloaiYour agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.
piyush-bhor/cve-2024-11394Technical Details and Exploit for CVE-2024-11394
