Version updated for https://github.com/taoq-ai/ziran to version v0.8.0. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary ZIRAN is an AI agent security testing tool designed to identify vulnerabilities in agents that utilize tools, memory, and multi-step reasoning. It automates the discovery of dangerous tool combinations, detects side effects from agent actions, and executes multi-phase attack campaigns guided by a knowledge graph.

Version updated for https://github.com/taoq-ai/ziran to version v0.7.0. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary ZIRAN is an AI agent security testing tool designed to identify vulnerabilities in AI systems, including agents with tools, memory, and multi-step reasoning. It automates the discovery of dangerous tool combinations, execution-level side effects, and multi-phase attack paths using graph-based analysis and autonomous pentesting.

Version updated for https://github.com/taoq-ai/ziran to version v0.6.1. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes.

Version updated for https://github.com/taoq-ai/ziran to version v0.6.0. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary ZIRAN is a security testing tool designed to identify vulnerabilities in AI agents, including those with tools, memory, and multi-step reasoning capabilities. Unlike traditional security tools that focus on testing LLMs or web applications, ZIRAN targets the unique attack surface of AI agents by analyzing tool chains, multi-phase campaigns, adaptive attacks, and multi-agent coordination.

Version updated for https://github.com/taoq-ai/ziran to version v0.5.0. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary ZIRAN is a security testing tool designed to identify vulnerabilities in AI agents, including those that use tools, retain memory, and perform multi-step reasoning. It automates the analysis of agent-specific attack surfaces, such as tool chain interactions, multi-agent coordination, adaptive attack campaigns, and protocol support.

Version updated for https://github.com/taoq-ai/ziran to version v0.4.0. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary ZIRAN is a security testing tool designed to identify vulnerabilities in AI agents, including those with tools, memory, and multi-step reasoning, rather than focusing solely on LLMs or web applications. It automates tasks such as tool chain analysis, multi-phase attack simulation, and remote scanning of agents over various protocols (REST, OpenAI, A2A, etc.