DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Security & Access DSH plugins — Page 21

CATEGORY

Security & Access DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1035Memory & Context1312Coding & Developer Tools2813UI & Customization3666Integrations & Communication1920Vision & Media617Search & Research866Security & Access1264Models & Usage1681Productivity & Workflow2252

All plugins

1265 plugins
Mv0.4.0
@ddtcorex/dsh-maestro-guard

Maestro Guard

Maestro Guard — pre-execute safety gate: native DSH approval prompts, parsed command-surface rules, decision journal

security-accessdeveloper-tools★ 1↓ 0
Updated 9/22/2026
Wv0.2.0
dsh-wsl-secret

Wsl Secret

DeepSeek Harness WSL plugin: pass/age secrets with allowlist; list/exists; secret_to_env without dumping values into chat.

security-access★ 1↓ 0
Updated 9/22/2026
v1.5.0
dsh-research-check

Research Check

Evidence-chain and conformance checks for any deliverable inside DeepSeek Harness: turn a requirements document (competition rules, journal guidelines, acceptance criteria, tender documents) into an executable spec and grade the deliverable against it; trace every number to a provenance ledger; audi

security-access★ 1↓ 0
Updated 9/22/2026
Cv0.1.1
@dsh-external/dsh-client-ui-permission-presets-jev

Client Ui Permission Presets Jev

Jev-branded fork of @deepseek-ai/dsh-client-ui-permission-presets: the Auto review mode reads "Auto Review Jev", keeps its EXP badge, and carries its own shield+sparkle glyph

security-accessui-customization★ 1↓ 0
Updated 9/22/2026
v2.0.2
dsh-permissions

Permissions

DeepSeek Harness permission rule engine: four rule levels—hard/deny/ask/allow (hard takes precedence over full access), global and workspace scopes, wildcard path protection, a visual draft-style editor, and rules persisted in self-managed JSON

security-access★ 1↓ 0
Updated 9/22/2026
Tv0.1.0
dsh-typesafe

Typesafe

TypeSafe Jev (System One decision model) for DeepSeek Harness: typed decisions in three question primitives, confidence-gated routing, a cost meter, and an automatic prompt-injection guard over untrusted tool results.

security-accessagents-orchestration★ 1↓ 0
Updated 9/22/2026
Ev0.2.0
dsh-egress-guard

Egress Guard

Runtime security gate for DeepSeek Harness: egress host allowlist, secret redaction in tool results, and an append-only audit log

security-access★ 1↓ 0
Updated 9/22/2026
Pv1.0.0
dsh-plugin-sirchmunk

Plugin Sirchmunk

DSH-native Sirchmunk settings plugin for graph, cluster, monitoring, history, and privacy workflows.

security-accessui-customization★ 1↓ 0
Updated 9/21/2026
Sv9.2.2
skills-summarize-audit-skill

Skills Summarize Audit Skill

DeepSeek Harness bundle that registers the skills-summarize-audit skill pack on ctx.skills.

security-access★ 1↓ 0
Updated 9/20/2026
Cv0.1.1
dsh-credential-manager

Credential Manager

Named user credentials for DeepSeek Harness: model-facing credential tools, secrets behind the ctx.credentials seam, DSH_CM_* shell variables, and a Settings → Credentials page

security-access★ 1↓ 0
Updated 9/19/2026
Av0.1.0
dsh-allow

Allow

DeepSeek Harness 权限记忆插件：把某类命令加进允许列表，之后同类命令不再询问。 / Remember sandbox-escalation approvals so the same commands stop asking.

security-accessmemory-context★ 1↓ 0
Updated 9/18/2026
Tv0.1.5
@zhaolianghz/dsh-turnscope

Turnscope

Turn-level safety inspection, change attribution, safe rewind, and isolated retry for DeepSeek Harness coding sessions.

developer-toolssecurity-access★ 1↓ 0
Updated 9/17/2026
Fv0.1.0
dsh-fingerprint-signature

Fingerprint Signature

Human verification gate and context variables for DeepSeek Harness

security-access★ 1↓ 0
Updated 9/17/2026
Zv1.0.4
@kolmopdf/dsh-zpdf

Zpdf

ZPDF tools for DeepSeek Harness with durable API-key settings and CLI configuration.

productivity-workflowsecurity-access★ 1↓ 0
Updated 9/16/2026
Vv0.2.6
@robbin810130/dsh-vault-plugin

Vault Plugin

DSH Vault Plugin: Frontend Privacy Lock for Projects and Conversations

security-access★ 1↓ 0
Updated 9/16/2026
Sv1.1.0
dsh-skillnotary

Skillnotary

Lock, verify and govern AI agent skills: a DSH plugin that makes the agent check what a skill can do before installing or updating it, and notice when it changes.

security-access★ 1↓ 0
Updated 9/16/2026
v0.3.2
dsh-privacy-protector

Privacy Protector

Privacy protector for DeepSeek Harness: per-session toggle, syntactically pseudonymize PII before it reaches the model, restore after response.

security-access★ 1↓ 0
Updated 9/16/2026
Av0.1.14
dsh-agent-gate

Agent Gate

Claw/session permission gate for DeepSeek Harness. Intercepts tools by tiered permissions, routes them through one-time approvals, and records audits. The official sandbox is enforced by the permission plugin.

security-access★ 1↓ 0
Updated 9/15/2026
Sv0.2.30
dsh-session-permissions

Session Permissions

Layered session permissions for DeepSeek Harness. 有效权限 = 官方 ∩ Agent ∩ 本会话；Claw 会话钉官方沙箱（只紧不松）。

security-access★ 1↓ 0
Updated 9/15/2026
Wv1.0.0
dsh-web-search-nokey

Web Search Nokey

Keyless web search for DeepSeek Harness. Fixes the web_search 401 on credits-based setups (Trae, WorkBuddy) without an API key.

search-researchsecurity-access★ 1↓ 0
Updated 9/15/2026
Mv1.0.0
mcp-cap

Mcp Cap

What can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.

security-access★ 1↓ 0
Updated 9/14/2026
Kv0.2.1
dsh-kubectl-guard

Kubectl Guard

A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.

security-accessdeveloper-tools★ 1↓ 0
Updated 9/13/2026
Wv0.1.0
@dsh-external/dsh-wechat-status

Wechat Status

Persistent WeChat login watchdog for DSH: polls the dsh-wechat bridge status and shows a Web overlay banner when the session drops and re-scanning is required. AI-generated, educational use only.

integrations-communicationui-customizationsecurity-access★ 1↓ 0
Updated 9/12/2026
Lv1.0.1
dsh-loopback-bridge

Loopback Bridge

Unlock DSH Web settings and credentials when you open the UI from a LAN IP or public hostname

security-access★ 1↓ 0
Updated 9/12/2026
Rv0.2.0
dsh-rule-lens

Rule Lens

规则透镜（RuleScope Lens）—— DeepSeek Harness 本地插件：AGENTS.md / rules 分层规则加载可视化、64KB 预算治理、写回防护与 FORBID 硬拦截、规则 Lint 与遵守率统计 | Rule visibility, budget governance & hard guards for DSH

security-access★ 1↓ 0
Updated 9/12/2026
Sv1.1.0
dsh-security-doctor

Security Doctor

One-click local security checkup for the DeepSeek Harness Web UI: a sidebar button that runs read-only checks (!!js config, third-party plugins, credential file permissions, instruction files, endpoint config, protection services) and shows a severity-graded report, plus an experimental opt-in guard

security-access★ 1↓ 0
Updated 9/11/2026
Hv1.0.0
dsh-hermes-security-audit

Hermes Security Audit

Free security audit for Linux servers — no API keys, no paid tools. Scans for viruses (ClamAV), rootkits (rkhunter + chkrootkit), SSH brute force, crypto miners, exposed credentials, and open ports. 1

security-access★ 1↓ 0
Updated 9/11/2026
Pv0.1.1
dsh-plugin-auto-review

Plugin Auto Review

Provider-backed automatic approval review for DeepSeek Harness.

security-accessdeveloper-tools★ 1↓ 0
Updated 9/11/2026
Gv0.1.0
dsh-gov

Gov

Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov

security-accessmodels-usage★ 1↓ 0
Updated 9/11/2026
Lv0.1.0
@dsh-external/dsh-llm-approver

Llm Approver

LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.

security-accessmodels-usage★ 1↓ 0
Updated 9/10/2026
← Previous1…1920212223…43Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in