
fastgpt-sandbox-audit
FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

Sentinel detection lab for MCP attack chains: CVE-2026-26118 SSRF token theft, tool poisoning, cross-server exfiltration, identity post-exploitation.…

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Zero shot vulnerability discovery using LLMs

A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Expose and detail an unauthenticated stored XSS vulnerability in the Google Cloud Vertex AI Python SDK affecting versions 1.98.0 to 1.130.9.

CVE-2025-67511: Tricking a Security AI Agent Into Pwning Itself

Real-time guardrails for Claude Code tool calls.

Moxy is an open-source DAST tool designed for modern web application security testing. It provides an easy-to-use interface with agentic capabilities…

image scaling attacks for multi-modal prompt injection

A tool which can be used to generate password list or dictionary from the details of the target

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data…

Guardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate…

Professional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading…