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.
DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。
9 个项目,匹配「packages」
hashgraph-online
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
yogsoth-ai
900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
wsxwj123
Independent plugins for DeepSeek Harness, organized as isolated packages in one monorepo.
leechen298
Generate Function, MCP, Agent Skill, and offline test packages from existing code; installable as a DeepSeek Harness bundle.
LA7-F
可以让你的dsh中的“Cordis插件”变得可管理,可一键生成安装包|Make the "Cordis plugins" in your dsh manageable and generate installation packages with one click.
Fectivnfy112357
crossplug — AI coding-agent plugin bridge: convert plugins between DSH / MiniMax Code (mcode) / pi, agent-plugins.org 1.0.0 packages, pi extensions; dual-side installers
Saikel-Orado-Liu
Archived-session management (show/unarchive/permanently delete) for the DSH Web GUI, with zero changes to official packages.
zoahdev
Plugin discoverability for DeepSeek Harness: search npm + awesome-dsh-plugin, look up packages, browse the curated list — from inside dsh agents (answers discussion #1715).
chendengyuanxm
Static security audit for dynamic Cordis plugins in DeepSeek Harness (DSH): rule-based source scanning, risk reports injected into tool results, and user-approval escalation before activating high-risk plugin packages. 动态 Cordis 插件静态安全审查。