awesome-dsh-plugin — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Anil-matcha · Agent Tool · ★ 987

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is awesome-dsh-plugin safe to install? View the security audit →

About awesome-dsh-plugin

Awesome DSH Plugin A curated guide to DeepSeek Harness () — DeepSeek's open-source, everything-is-a-plugin coding agent — and the best community plugins built on it. DeepSeek Harness is a runnable coding agent (Web UI + headless) built on Cordis, where every part of the system — models, tools, sandboxes, session storage, UI, even the agent loop itself — is a swappable plugin. That architecture has produced a large, fast-moving plugin ecosystem: well over a thousand community plugins at last count. This list exists to make that ecosystem easy to scan: what a plugin does, in one line, sorted into the category you'd actually go looking under. [!WARNING] Installing any third-party plugin runs its code on your machine with your own permissions. Being listed here is not a security review — read the source before installing, especially for plugins that touch credentials, the network, or your filesystem. ▶ Watch: Awesome DSH Plugin — Top 10 DeepSeek Harness Plugins You Need Contents What is DeepSeek Harness? Getting Started [Plugin Categor

agent-harnessai-agentai-agentsautonomous-agentawesomeawesome-listclicoding-agentcordisdeepseek

Quick Facts

Stars987
Forks247
CategoryAgent Tool
Quality Score63.9944971284845/100
Open Issues2
Last Updated2026-08-25
Created2023-05-06
Platformsbrowser, cli
Est. Tokens~24k

Compatible Skills

These tools work well together with awesome-dsh-plugin for enhanced workflows:

awesome-dsh-plugin alternative? Top 6 similar tools

Looking for a awesome-dsh-plugin alternative? If you're comparing awesome-dsh-plugin with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • wesight by freestylefly · ⭐ 893

    Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus

  • rea by morluto · ⭐ 398

    Reverse engineer anything with agents, from app behavior down to native binaries.

  • memsearch by zilliztech · ⭐ 2.6k

    A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown a

  • commonly by Team-Commonly · ⭐ 1.3k

    Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and works

  • oh-my-agent by first-fluke · ⭐ 1.3k

    The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent j

  • mnemon by mnemon-dev · ⭐ 558

    LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. W

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Frequently Asked Questions

What is awesome-dsh-plugin?

awesome-dsh-plugin is A curated list of plugins for DeepSeek Harness (dsh) - DeepSeek Harness plugin ecosystem. It is categorized as a Agent Tool with 987 GitHub stars.

How do I install or use awesome-dsh-plugin?

You can find installation instructions and usage details in the awesome-dsh-plugin GitHub repository at github.com/Anil-matcha/awesome-dsh-plugin. The project has 987 stars and 247 forks, indicating an active community.

What are the best alternatives to awesome-dsh-plugin?

The top alternatives to awesome-dsh-plugin on Agent Skills Hub include wesight, rea, memsearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools