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

Reverse-engineering workbench built on Ghidra's decompiler with a native Java-free engine, AI-assisted function analysis, byte patching, sandboxed…

Sentinel — DeanWay Labs' inbound governor. Guards what an AI agent hears: world content is data, never orders. The mirror of QuietOS.

AI chat-box pentesting tool in C: fires language (SQLi/NoSQL/XSS/SSTI) and prompt injection payloads at chat interfaces and flags the ones that bite

OWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…

Agentic harness that automates vulnerability discovery and validation, orchestrating AI-driven analysis workflows to confirm exploitable findings.

OWASP project focused on security for large language model applications, covering LLM-specific risks, testing guidance, and mitigation practices.

OWASP guide defining a standardized penetration testing methodology for humanoid, industrial, and autonomous robots, covering ROS/ROS2, DDS, CAN bus,…

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Creates CycloneDX Bill of Materials (BOM) for your projects from source and container images. Supports many languages and package managers. Integrate…

Claude Code and Codex skill for finding potentially vulnerable Brotli copies and guiding updates for CVE-2026-111497.

Scans Shodan for publicly exposed Ollama and llama.cpp servers, enumerating hosts, locations, and available models for security research.

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

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…

Research on persistent prompt injections via memory features in Claude, Gemini, and ChatGPT, with reproduction steps, datasets, and proofs for…

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

Jailbreak vulnerability across early-exit depths LLMs. Published at NeurIPS 2026 in the FLMSec workshop

Reachability triage for vulnerability scans. Feeds scanner findings to an LLM agent that reads your source and decides which CVEs are actually…

Reproducible Colab pipeline that grounds six AI Security Literacy competency dimensions in public benchmarks and survey microdata, producing figures,…