Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
Security
DeepSeek Harness Plugins.
Explore DeepSeek Harness security plugins for permissions, sandboxing, policy, secret handling and defensive workflows. Review the public source and declared license before installation.
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
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.
DeepSeek Harness 破甲一体化安全分析插件:Android · Web · Native · Protocol · Malware · AI-Security 全领域聚合(9 bundle + 1 preset)
让你通过浏览器安全地远程使用 DeepSeek Harness:登录、MFA 两步验证、角色权限和远程文件预览。 | Use DeepSeek Harness securely in a remote browser with login, MFA, roles, and remote file preview.
Server-grade gateway that turns DeepSeek Harness into a multi-tenant platform: remote access + auto HTTPS, subuser permissions & quotas, sandbox enforcement, encrypted auth, audit log.
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
Plugin family for the DeepSeek Harness (DSH) Web GUI: a pnpm monorepo with a plugin template, dev kit, and one-command all-in-one bundle — Codegraph, env & secrets, MCP config, profiles, prompts, RSS digest, global search, and terminal panel.
Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/directory support.
为 DeepSeek Harness 提供电脑控制插件:新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入(目前支持macos)|Accessibility-first macOS Computer Use bundle for DSH with fresh observations, stale-state rejection, scoped permissions, and safe input.
Create and manage sandboxed JavaScript tools for DeepSeek Harness with a Monaco editor and model-driven tool lifecycle.
Security-audit skill pack + plugin_vet supply-chain gate for DeepSeek Harness (dsh): 8 bilingual agent skills (secret scan, dependency audit, supply-chain review, prompt-injection review, audit orchestration, threat modeling, vuln intel, incident response) plus the plugin_vet automated pre-install scanner. Apache-2.0.
Login gate for the DeepSeek Harness (dsh) web surface: password or shared-token sign-in, optional TOTP two-factor, session cookies, rate limiting, self-service password change and a user-management CLI. | DeepSeek Harness 网页版登录门插件:账号密码或共享令牌登录、可选 TOTP 两步验证、会话 cookie、登录限速、自助改密,附用户管理 CLI。
为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档,危险或不确定操作仍转人工审批。An auto-approval permission preset between workspace-write and full access for DeepSeek Harness.
DSH 本机安全审计插件:配置/插件来源/会话/网络暴露面,只读脱敏风险报告
RMB/USD token-billing plugin for DeepSeek Harness (dsh web): official-policy auto pricing with peak/off-peak hours, per-message ledger, account balance, locale-driven currency display. 人民币/美元 token 计费插件
Security audit for DeepSeek Harness plugins: static permission profile with file/line evidence + a runtime sentinel gating credential access and unknown-host egress · DSH 插件安全审计:静态权限画像(附文件/行号证据)+ 运行时哨兵,触及凭证或向未知主机外发数据时先请你批准
Content-addressed receipts for skills actually loaded by DeepSeek Harness
A community-built DeepSeek Harness plugin.
Declarative deny-by-default tool policy plugin for DeepSeek Harness
Automode for DeepSeek Harness: a fourth permission preset — full access with an LLM classifier as the only gate before every tool call.
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
DeepSeek Companion Enterprise — DeepSeek Harness 企业级伴侣插件:安全审计与 DLP、团队协作与知识管理、任务编排与断点续跑、多模型竞技场、执行轨迹分析、Prompt 工程工作台。
原生UI界面。面向 DeepSeek Harness Web 的虚拟机沙箱插件:它基于 OrbStack 为每个会话提供独立的 debian/alpine 沙箱虚拟机,在会话视图环中新增「虚拟机」页签,支持查看/启动/休眠/删除和详细配置展示,同时为模型提供 `vm_list`、`vm_create`、`vm_exec`、`vm_delete` 工具,并内置全局运行上限、闲置自动休眠、归档/删除自动清理等资源治理能力。
SecurStack adapter for DeepSeek Harness: run repository security scans, policy gates, doctor diagnostics, and JSON CLI results from safe AI-agent tools.
?? for DeepSeek Harness: first security plugin for dsh. Scans skills/MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, credential leaks. DSH ????????
OpenAI Codex Security for DSH, zero-setup — 13 audit skills + 5 scan tools in a session preset, plus an auto-audit gate for new plugins, running on your local model with no API keys.
Policy-enforced, evidence-first governed workflows for DeepSeek Harness agents.
A community-built DeepSeek Harness plugin.
DSH 代码安全审查插件:40+ 确定性规则与密钥熵检测,支持 git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite。
One-click local security checkup button for the DeepSeek Harness (DSH) Web UI: read-only checks (!!js config, third-party plugins, credential file perms, instruction files), severity-graded report, plus AI-usable security-review & secure-development guides. / DSH 安全医生:一键本机安全体检插件
A drop-in dsh web profile that adds the **Self Checking** sandbox mode to DeepSeek Harness (dsh)
macOS backend for dsh-witness/dsh-anchor: uchg + sandbox-exec sandbox recipes. Every claim carries an experiment number.
Native DeepSeek Harness workbench for evidence-first vulnerability research, reproduction, and reporting.
DSH agent-fleet hygiene audit plugin: credential-file permissions, embedded git-remote credentials (masked), provider token literals. Read-only, zero-dependency, deterministic.
DeepSeek Harness plugin that turns silent tool failures into loud ones: a tools/post-execute policy that matches warning signatures in successful tool output and blocks the result or attaches a notice
Security guard for DeepSeek Harness (dsh): static scan for malicious code, prompt injection and token waste, runtime interception, /scan, plugin_scan, web panel and allowlist | DeepSeek Harness 安全守卫插件:恶意代码/提示词注入静态扫描、运行时拦截、/scan、plugin_scan、Web 面板与白名单
Security assessment workflows for DeepSeek Harness
microsandbox支持
Render HTML design prototypes directly in DeepSeek Harness with a canvas tab for visual review, annotation, and sandboxed previews.
Interactive ACP v2 bridge for DeepSeek Harness (dsh) — streaming, run-state reporting, permissions. ALwith Desktop is its reference client.
✋ Hands for your DeepSeek Harness agent — autonomous browser operation by accessibility refs, with a permission model that follows your dsh session.
Plugin health audit for DeepSeek Harness: sync the GitHub dsh-plugin topic into a local catalog, probe npm, static-scan for security, score every plugin, and rank them in a web leaderboard.
A community-built DeepSeek Harness plugin.
Find DSH plugins by asking in plain language, then security-scan them before install
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。
Deterministic release-risk checks and quality gates for DeepSeek Harness
Interactive terminal agent (fork of DeepSeek Harness): Claude Code-style REPL — full-screen UI, markdown rendering, session stats, permission cycling, custom OpenAI-compatible providers.