Rogue
正常简介
AI Agent Evaluator and Red Team Platform. Provides systematic security evaluation and adversarial testing tools to discover and fix vulnerabilities in agent systems.
相关项目
Agent Governance Toolkit
1.1k · Python
Microsoft's AI Agent Governance Toolkit providing policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
securityevaluationpython +2
Purple Llama
4.1k · Python
Meta's set of tools to assess and improve LLM security, including safety benchmarks, prompt injection detection, and output auditing to help evaluate and enhance the safety of large language models.
securityevaluationpython +2
Agentic Radar
953 · Python
A security scanner for LLM agentic workflows. Automatically detects security vulnerabilities, prompt injection risks, and permission violations in agent pipelines before deployment.
securityagentpython +2
HolmesGPT
2.2k · Python
A CNCF Sandbox SRE Agent that automatically analyzes infrastructure logs and metrics to assist with incident diagnosis and system operations.
observabilitypythonagent +2