#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Curated systematic literature review of 756+ papers on LLM applications in cybersecurity, covering threat intelligence, vulnerability detection,…

On-device AI browser automation using WebLLM. No cloud, no API keys, fully private.

Secret-Use Delegation Protocol — protocol-level secret use for agentic systems

Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US…

A static + runtime security scanner for MCP (Model Context Protocol) servers

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

PoC for CVE-2025-62593: unauthenticated RCE in Ray (CISA KEV). Stdlib-only Python.

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

Research code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements,…

All the materials for Gareth Heyes' Black Hat talk: CSS: the bomb inside your inbox.

CVE-2026-73678 — MindsDB Minds Platform unauthenticated RCE via scratchpad exec (CVSS 10.0). Verified end-to-end with real LLM

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

AI-driven penetration testing agent that connects to a Kali box, autonomously runs security tools, analyzes results, and iterates through…

Cross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…

Open-source adversary emulation for AI agents and MCP servers.

A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security.