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

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

A transparent PII redaction proxy for LLM API traffic. Sits between an application and an LLM provider (currently Anthropic), pseudonymizing…

OWASP Incubator project: detects credentials exposed in browser-delivered content (JavaScript, config responses, live traffic).

Security awareness training tool for authorized phishing simulations and internal IT audits

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

AIO Cloud Managment Server

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

Proxy server that wraps MCP servers with behavioral profiling, security scanning, risk gating, and safe execution. Detects prompt injection,…

Know what changed inside your Electron release: diff two builds for IPC, preload, windows, fuses and hosts, with file:line. CLI, CI gate, MCP server.

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

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

Sigma detection rules for AI agent security monitoring

Secure local REST, CLI, MCP, and agent bridge for IDA Pro 9.x

Kernel-enforced authority and runtime security for Linux systems, autonomous software, and AI agents.

Fine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…

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