onlyqzq/dsh-riskproof 预览 preview

onlyqzq/dsh-riskproof

Plugin插件 Native原生 ⭐ 7 Apache-2.0 Approval & Security审批与安全

Risk-aware approval layer for high-risk AI Agent tool calls

Project Overview项目介绍

This is a DSH-native plugin that provides provenance-aware execution security for tool calls within the DeepSeek Harness agent framework. It hooks into DSH's native tool pipeline at the pre-execute and result stages, tracks data origins across multiple sequential tool calls, detects risky cross-tool data flows, and blocks dangerous execution before any sensitive side effects occur. To install from the current release candidate, you first build the npm tarball from source with npm pack --pack-destination artifacts, then run dsh plugin add on the generated tarball, and the plugin registers automatically after a DSH profile restart.

It adds a persistent security beacon to the side of your DSH conversation, which updates automatically every time a tool call completes. You can click the beacon any time to open a compact overview that shows call distribution statistics, the last 24 risk checks, up to three recent risk chains, and clear counts of allowed, blocked, and attention-needed calls. You can also use a set of /riskproof DSH commands to manually pull a full provenance trace, adjust task scope to read-only or local-only mode, or run an isolated demo rehearsal of risk detection. This plugin targets DSH users who want extra protection against unintended sensitive data flows across tool calls.

RiskProof is released under the permissive open-source Apache 2.0 license, so it is free to use, modify, and distribute, with no associated cost for any use case. The current 0.3.0 release candidate has been fully validated on DSH versions 0.1.0-rc.7 and 0.1.2-rc.1, and works on both Chrome desktop and narrow-viewport DSH web instances. It is important to note that RiskProof does not replace core system security tools like OS process sandboxes, network firewalls, endpoint malware scanners, or credential vaults, and it does not provide full semantic data loss prevention. It only adds provenance tracking for observable DSH tool call flows.

这是一款专为 DeepSeek Harness (DSH) 开发的原生执行安全插件,用于追踪工具输入数据的来源,检测风险跨工具数据流,在危险副作用执行前终止操作。它直接挂载到 DSH 的工具调用管道,在预执行和结果阶段介入完成污点分析与策略判定,安装后会自动在对话侧边生成持久安全 beacon 入口。你可以通过构建 npm 压缩包后使用 dsh plugin add 命令完成安装。

面向需要提升 DSH 代理工具调用安全性的开发人员与普通用户,适合关注数据泄露风险、需要拦截敏感数据跨工具流动的场景。使用时,普通工具调用会自动更新安全 beacon 状态,用户点击即可打开概览面板查看调用分布、最近风险链和统计数据,也可以通过 /riskproof 系列命令手动触发溯源报告、调整任务权限模式。插件使用确定性分析,不依赖大模型做分类判定。

本插件遵循 Apache-2.0 开源协议,无需付费使用,当前 0.3.0 版本候选已在 DSH 0.1.0-rc.7 到 0.1.2-rc.1 多个版本验证通过,支持 Chrome 桌面端和窄屏 Web 环境。它不替代操作系统沙箱、网络防火墙、端点安全等基础安全设施,也不提供全语义数据泄露防护,仅针对可观测的工具调用流程提供可配置的来源溯源防护。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 7 stars - very few users, little community feedback星标只有 7,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile web add dsh-riskproof@0.4.1

把 onlyqzq/dsh-riskproof 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

RiskProof

Provenance-aware execution security for DeepSeek Harness.

Track where tool inputs came from. Detect risky cross-tool data flows. Stop sensitive side effects before execution.

English · 简体中文

Start here

Goal Read
Install and try it Quick Start · Installation
Tune protection and task scope Configuration
Understand or contribute to the project Architecture · Development
Find security boundaries and version records Documentation index

See protection beside your conversation

A persistent RiskProof security beacon sits beside the DSH conversation. Ordinary tool calls update it automatically. Click to open a compact overview; activity never opens it for you.

Persistent RiskProof beacon

  • Waits honestly for tool activity; there is no continuous simulated scan.
  • Shows pending execution receipts and briefly acknowledges newly checked calls.
  • Displays a call-distribution ring, the last 24 checks and up to three recent risk chains.
  • Follows the selected conversation and removes stale charts when its connection is unavailable.
  • Separates initial sync from disconnection, offers manual reconnect, and displays task scope and record limits.

Live call distribution and provenance

Real DSH Web screenshots; a local test model produced these records through the actual Agent/tool pipeline. Normal use does not require a rehearsal.

The chart counts calls with no triggered risk, calls blocked by RiskProof, and calls needing attention. It does not invent a safety score. Observe mode, disabled recording and disabled detection features are identified. Counts cover retained records in the current plugin run. Not triggering a rule does not establish that an operation is safe.

Commands remain secondary entries; long output is collapsed by default:

Need DSH command
Open the compact overview /riskproof
Read the text provenance report /riskproof trace
Restrict to inspection /riskproof task read-only
Keep tool capabilities local /riskproof task local-only
Restore ordinary task scope /riskproof task standard
Optional isolated rehearsals /riskproof demo

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev DeepSeek-Harness-Pet 下一个 Next dsh-code-index →