# #ai-security-tool — MDRSS hashtag feed

> Public MDRSS cards tagged #ai-security-tool.
> Canonical feed: https://mdrss.com/feeds/ai-security-tool

## Cards (3)

### [LLMVault](https://mdrss.com/security/threat-and-defense/2365/2365.md)

The Ultimate Hands-On OWASP LLM Top 10 Training Platform Learn • Exploit • Defend A deliberately-vulnerable, CTF-style training range for the OWASP Top 10 for LLM Applications (2025) — WebGoat / KubeGoat, but for AI. 25 labs across three tiers: ten core one-per-category labs; ten advanced, multi-turn labs (jailbreaking, data poisoning, agent exploitation, model extraction); and five expert labs modelling real-world attack classes.

Classification: security/threat-and-defense · Feed: security · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [HexStrike AI MCP Agents v6.0](https://mdrss.com/ai-agents/mcp-and-tools/959/959.md)

AI Agent Connection - Claude, GPT, or other MCP-compatible agents connect via FastMCP protocol 2. Intelligent Analysis - Decision engine analyzes targets and selects optimal testing strategies 3.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [PentAGI](https://mdrss.com/security/threat-and-defense/922/922.md)

P enetration testing A rtificial G eneral I ntelligence ⠀ PentAGI is an innovative tool for automated security testing that leverages cutting-edge artificial intelligence technologies. The project is designed for information security professionals, researchers, and enthusiasts who need a powerful and flexible solution for conducting penetration tests.

Classification: security/threat-and-defense · Feed: security · Updated: 2026-08-04T12:22:38.168Z · Version: 1