The open-source diagnostic for AI misalignment. 32 tests across fabrication, manipulation, deception, unpredictability, and opacity. Provider-agnostic. Runs against OpenAI, Anthropic, Bedrock, Azure, Gemini, and more. Letter grade in under 5 minutes, content-addressed manifest for bit-identical replay. Built by iMe.

AIGoat - Open-source AI security playground for LLM red teaming. AI Goat provides hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.

Open-source AI security firewall. 81 engines for PII detection, prompt injection defense, MCP security, and egress classification. Local-first. Zero cloud dependency.

nod is a platform-agnostic, rule-based linter that ensures AI/LLM specifications contain critical security and compliance elements before any agentic or automated development begins.

AI Security Öğrenme Rehberi: Yapay zeka güvenliği alanında kariyer yapmak isteyenler için pratik rehber. Python temellerinden bug bounty süreçlerine, Türkiye pazarındaki fırsatlar ve öğrenme stratejileri.

🛡️ Gemini API destekli, kaynak kodlarındaki SQLi ve XSS zafiyetlerini tespit eden yapay zeka tabanlı analiz motoru ve LLM tehdit alanı güvenlik araştırması.

AI agent discovery and security assessment platform with vulnerability testing, risk scoring, and compliance mapping

Blackwall LLM Shield is an open-source AI security toolkit for JavaScript and Python that protects LLM apps from prompt injection, sensitive data leaks, unsafe tool calls, and hostile RAG content with prompt sanitisation, PII masking, output inspection, policy enforcement, and audit trails.

Blackwall LLM Shield is an open-source AI security toolkit for JavaScript and Python that protects LLM apps from prompt injection, sensitive data leaks, unsafe tool calls, and hostile RAG content with prompt sanitization, PII masking, output inspection, policy enforcement, and audit trails.

Hands-on demos for the Pluralsight course: Generative AI Data Privacy and Safe Use for Developers. Covers PII masking, prompt injection attacks and defenses, five guardrail rail types (input, retrieval, dialog, execution, output), evaluation release gates, and dashboards mapped to EU AI Act, NIST AI RMF, and ISO/IEC 42001.

Reverse-engineer any MCP server's tool surface in 30s. Companion to capnagent.

Cross-model LLM jailbreak research — EASL technique confirmed against DeepSeek (HIGH) and Google Gemini (CRITICAL). Disclosed April 2026. #LLMSecurity #AIRedTeam #PromptInjection

APM Security Demo App 005 — Go with lockfile integrity violations

An interactive web application that generates comprehensive security playbooks for mitigating the OWASP Top 10 vulnerabilities specific to Large Language Model (LLM) applications. The application consists of a Flask backend that leverages the OpenAI API to generate detailed playbooks, paired with a simple HTML/JavaScript frontend.

AWS AI Security Lab: Prompt Injection, LLM Data Leakage, IAM Misconfiguration, Clouwatch Detection, and Secure Architecture

Hands-on APM Security scanning workshop — step-by-step labs for agent config file security, OWASP LLM Top 10, and Power BI reporting

Drop-in prompt injection defense for LLM apps and AI agents — detect, block, and audit injection attacks in real time

APM Security Demo App 002 — Flask with Base64/exfiltration violations

Defensive AI security red-team harness for LLM, RAG, and AI-agent systems with safe local demo, dashboard, redacted evidence, CI gates, and governance mapping.