Dsh Plugin Audit — Security skill for Claude Code
Agent Skill for DeepSeek Harness (DSH):装第三方插件前的静态安全审计 —— 扫出 eval、patch 层 !!js、安装期脚本、开机自启、凭据复制、出网域名与提示词注入面.
How to install Dsh Plugin Audit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open kiterunner1/dsh-plugin-audit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Dsh Plugin Audit does
Agent Skill for DeepSeek Harness (DSH):装第三方插件前的静态安全审计 —— 扫出 eval、patch 层 !!js、安装期脚本、开机自启、凭据复制、出网域名与提示词注入面。Audit third-party DSH plugins before installing. Works with DSH, Claude Code, Codex, Cursor & any Agent Skills compatible agent.
Alternatives in Security
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Eval Audit — /eval-audit — Batch Skill Evaluation 216 ★
- Loongsuite Pilot — Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cu 150 ★
README
plugin-audit
中文 · English
**装插件之前,先看一眼它要碰什么。**
一个给 [DeepSeek Harness(DSH)](https://github.com/deepseek-ai/deepseek-harness) 用的 [Agent Skill](https://agentskills.io):一次静态安全审计,把 `eval`、patch 层 `!!js`、安装期脚本、开机自启、凭据复制、出网域名、子进程调用、提示词注入面全部扫出来,按「硬否决 / 待确认能力 / 观察项」三层给出结论。
第三方插件是**别人写的、与你同进程同权限运行的代码**。它能不能跑,装之前几乎没人看得见;装之后又不一定回得去。这个技能把「装之前先看一眼」变成一条命令。
**注意:** 本项目为社区项目,与 DeepSeek 官方无隶属关系,亦未获官方背书。
为什么需要它
DSH 对「模型行为」有生产级防护(沙箱、权限、审批),但对「插件代码」没有安全设计。以下四条来自官方 Discussion [#454](https://github.com/deepseek-ai/deepseek-harness/discussions/454) 以及第三方插件安全审计报告:
| 事实 | 后果 |
|---|---|
| 插件与宿主同进程、同权限 | 插件能做的事 = DSH 能做的事 |
| 文件沙箱只挡「写」,不挡「读」 | 你的 ~/.dsh、.credentials.yaml、.ssh 都在可读范围 |
patch 层 !!js 表达式在加载期执行 |
光看 package.json 看不出任何异常,代码在装载时就跑了 |
| 恶意 bundle 安装即执行 | 而且事后 remove 清不掉已经落下的后门 |
也就是说:插件来源不明时,风险不在「功能不好用」,而在「你根本不知道它动了什么」。
它检查什么
脚本按三层归纳,全部是**模式匹配 + 上下文过滤**(跳过纯注释行,同一文件同一规则只算一条):
**硬否决项(VETO)——单项即可否**
| 项 | 命中内容 |
|---|---|
| 动态求值 | eval( / new Function / vm.runIn* |
| patch 注入 | !!js(加载期执行) |
| 安装期脚本 | postinstall / preinstall / prepare / prepublish |
| 开机自启 | 注册表 Run / schtasks / LaunchAgents / systemd unit |
| 凭据落盘 | 把 credential / .env / .ssh / id_rsa 复制到别处 |
**待确认能力(RISK)——不是指控,是「它有权做什么」**
| 项 | 命中内容 |
|---|---|
| 出网能力 | fetch / axios / WebSocket / net.connect |
| 遥测导出 | telemetry / `otel |
Related Skills
Secure Plugin Installer
Audit and gate third-party Claude Code plugins / OpenClaw skills before enabling them: capability enumeration,
Skill Lint
Security scanner for Claude Code / agent skills. Catches prompt injection, obfuscation, credential exfiltratio
Drift Detector
Keep third-party API integrations green — scan repos, audit for CVEs/EOL/vendor-API sunsets, deliver the repor
Cc Skill Audit
Security scanner & PreToolUse firewall for Claude Code third-party skills. Detects undisclosed telemetry, outb
Amazon Skills
Free AI agent skills for Amazon sellers— keyword research, competitor analysis, listing audit & more. Works wi
Polymarket Skills
Composable Agent Skills for Polymarket prediction market trading. Paper-trading-first, security-audited. Works
Related Agents
Ds Flash
DSH (DeepSeek Harness) worker on the flash tier - fast and cheap. Delegate simple, well-scoped subtasks: mecha
Dependency Vetter
Supply-chain security audit of a third-party package (npm today) at ONE exact resolved version, run BEFORE it
Integration Dev
External API and third-party system integration specialist for Home Assistant, ZoneMinder, weather services, a