Tag

Unified exposure management platform for automated vulnerability scanning, attack surface monitoring, and cloud security posture management.

Julius is an open-source LLM service fingerprinting tool that identifies Ollama, vLLM, LiteLLM, and 30+ other AI services running on network endpoints.

Lakera provides an AI-native security platform to accelerate GenAI initiatives, trusted by Fortune 500s and backed by AI red teams.

Neutral benchmark for evaluating prompt injection detection systems across 4,300+ inputs including jailbreaks and adversarial prompting.

MCPHammer is a security assessment tool for the Model Context Protocol. It helps red teams test LLM integrations for prompt injection and data leakage.

Offensive auditor for MCP servers. Detects RCE, tool poisoning, credential leaks, and SSRF across stdio, HTTP, and SSE transports.

MITRE ATLAS is a knowledge base of adversary tactics and techniques targeting AI systems, helping organizations secure AI deployments.

ModelScan: scans ML models for unsafe code, supporting H5, Pickle, and SavedModel formats, protecting against serialization attacks.

Moxy is an open-source DAST tool with agentic AI for modern web application security testing and automated pentesting workflows.

The OWASP AI Testing Guide provides a framework for assessing AI security, covering adversarial robustness, data poisoning, and privacy for AI systems.

OWASP unveils the Gen AI Red Teaming Guide, offering a structured approach to evaluating LLM and Generative AI vulnerabilities.

OWASP Gen AI Security Project provides resources, risk strategies, and global collaboration to secure LLMs, AI agents, and generative AI technologies.