安全与治理 插件 mirage strukto-ai The World's First Unified Virtual Filesystem For AI Agents agent-sandbox agent-tools ai-agents bash
安全与治理 插件 hol-guard hashgraph-online Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. agent-security ai-agent-security ai-agents ai-antivirus
安全与治理 插件 dsh-permission-rules PerryLink Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload. ai-safety allow-deny-ask approval cordis
安全与治理 技能 deepseek-harness-skillx drowned-fish1 DeepSeek Harness plugin for safely discovering, auditing, and adopting external Agent Skills — prompt-injection and AgentBaiting defense. agent-skills agentbaiting ai-agent claude-code