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

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack
Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

SafeForge is an open-source mobile app hub built on GitLab that enables developers to build, upload, and share applications in a secure, AI-verified…

CVE-2026-20685 - Draft or TODO

A font-based deception tool for red teaming, security research, and whatever else.

Pre-launch security checklist for AI-generated apps (Lovable, v0, Bolt, Cursor). 69 checks covering Supabase RLS, exposed keys, and prompt injection.…

Cryptographic terminal forensics and session replay for AI agents. Tracks, signs, and audits every command with provenance labels, replayable…

Provenance-aware Linux kernel vulnerability research harness used in the investigation of CVE-2026-53075

Evidence-driven Linux kernel vulnerability research harness used in the investigation of CVE-2026-31720

CVE-2026-67598 — Emlog Pro: disabled TLS certificate validation in AI assistant (MITM → API-key theft). CWE-295, CVSS 9.1. Reported by @IlhomjonR.

Cybersecurity writeups, walkthroughs, and technical notes by Nanashi Bx2.

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Security patches for unpatched llama.cpp vulnerabilities (CVE-2026-43626 through CVE-2026-43632) — Cyera Research

Agent Control Protocol (ACP) — Official English specification. Cryptographically verifiable authorization architecture for autonomous AI agents.

Proof-of-concept for CVE-2026-23001: demonstrates RCE through unsafe pickle deserialization in Hugging Face Transformers by crafting a malicious…

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

Automated security analysis pipeline that runs CodeQL queries on GitHub repositories and uses LLMs to classify and filter true vulnerabilities from…