Categories › Security & ops
Security & ops
1858 pluginsSecurity audits, usage metering, WSL and system tools — keeping it safe and measurable.
Sorted by downloads. 100 per page.
github:amwangfan/dsh-privacy-guard
Control panel for a local credential-redaction gateway in DeepSeek Harness: gateway and mo
↓ 0
github:AntaresCorn/dsh-auto-reviewer
Codex-style auto-review permission mode: adds an auto-review preset that auto-approves saf
↓ 0
github:apex-mochen/dsh-sandbox-arg-guard
Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (
↓ 0
github:ArisuYuuko/dsh-approval-explainer
Writes a model-generated annotation into every DSH escalation approval prompt — what the c
↓ 0
github:arrow949/dsh-turn-approval
Turn-scoped “Allow for this task” approvals: automatically allow matching `danger-full-acc
↓ 0
github:ateen18/dsh-plugin-security-review
Pre-install static security review and runtime guard for dsh plugins: deobfuscation decodi
↓ 0
github:BotonJ/dsh-plugin-sentinel
Static pre-install security auditor for plugin bundles: lifecycle scripts, dynamic executi
↓ 0
github:cdxiaodong/dsh-guardian
Agent security guardrail: intercepts and audits every tool call, requiring human confirmat
↓ 0
github:ChenLaoshiYF/dsh-mcpguard
Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous s
↓ 0
github:devil233-ui/dsh-auto-review-default
Puts sessions into the built-in Auto review permission preset: new sessions at creation, e
↓ 0
github:DevilSpiderX/dsh-workspace-only-plugin
Restrict the file access of agents in any sandbox mode (read-only / workspace-write / dang
↓ 0
github:DingZhiQi5596/dsh-plugin-guard
DSH Desktop plugin safety guard: self-repairs plugin load crashes and runs 8 core safety c
↓ 0
github:Dofang-C/dsh-file-integrity-check
Scan and fix Low integrity labels, non-inherited S-1-4 sandbox ACEs, and related Everyone
↓ 0
github:DSH-Raising-Plan/dsh-agent-gate
Advisory permission checks for DSH tool calls: risk tiers, a path sandbox (empty allowed_r
↓ 0
github:DWJZ/dsh-allow
Filesystem permissions for shell calls, granted per path and capability rather than per co
↓ 0
github:GDWhisper/dsh-web-startup-auth
Replaces the dsh web startup to allow binding 0.0.0.0, gated by username/password login: s
↓ 0
github:GooDAnDReaDY/dsh-dsml-artifact-guard
Sanitizes leaked DeepSeek DSML closing tags from model text streams.
↓ 0
github:heyuanliu3-byte/dsh-auto-preset
Restores the permission preset a session was last set to when that session is reopened; a
↓ 0
github:hhl123hhl/dsh-privacy-shield
Rewrites the model-visible copy of system, developer, user, assistant and tool messages in
↓ 0
github:IamNewHands/dsh-approval-gate
Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has rea
↓ 0
github:IFIAnder/dsh-loose-review
Reviews destructive shell commands with a model before they run, asks you to confirm or bl
↓ 0
github:iiiweiii/dsh-guardwall
Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk
↓ 0
github:JohnXu22786/safety-net
Destructive-command interception gate for dsh: parses shell semantics, judges risk against
↓ 0
github:JohnXu22786/secret-guard
Blocks agents from reading or writing sensitive files (.env, credentials, key material), m
↓ 0
github:kipozannaki/DSH-PDR-Plugin
Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app can
↓ 0
github:Ledas-as/-deep-seek-harness
Chinese progress guidance and user-confirmed project or global memory, respecting DSH Full
↓ 0
github:leetom314/dsh-risk-gate
Semantic risk grading and progressive authorization: classifies tool calls into safe/risky
↓ 0
github:LeslieWylie/dsh-fleet-audit
Read-only agent-fleet credential hygiene audit: credential-file permissions, embedded cred
↓ 0
github:lizhijie429/dsh-push-privacy-guard
Privacy guard for git workflows: before git commit, git push or gh repo sync it scans the
↓ 0
github:lmk2215/dsh-session-lock
Conversation lock for the DeepSeek Harness sidebar: every conversation row gets a lock but
↓ 0
github:lonelymoon87/dsh-guardian
Adds dangerous-operation policy checks, output redaction, and a security-review workflow.
↓ 0
github:LWLAymh/dsh-edit-guardian
File-change diff bar with keep/undo summary, plus dangerous-command approval and red highl
↓ 0
github:Martlet-Tech/dsh-approval-explain
Adds an Explain button to the approval card: one model call returns exactly three lines re
↓ 0
github:Mengshang-spec/dsh-plugin-trustlens
Read-only DSH plugin auditor with static scanning, current-session model review, and confi
↓ 0
github:MYCF711/dsh-sovereign
Host-plane sovereignty clause and content guard: appends user-held adjudication to the sys
↓ 0
github:MyRemme/dsh-computer-use-guard
Three-tier deny/ask/auto gate for the computer-use (cua-driver) tool family: each tool cat
↓ 0
github:NattoCB/dsh-safe-delete
Tools guard that moves agent-issued `rm` targets to the macOS Trash instead of deleting, w
↓ 0
github:nengong-ai/dsh-keychain-credentials
Pure JavaScript macOS Keychain credentials provider for DeepSeek Harness, replacing plaint
↓ 0
github:NEVSTOP-LAB/dsh-approval-mode
Adds an approval-mode toggle next to the permission selector: default approval keeps per-c
↓ 0
github:omdsh-dev/dsh-security-audit
Local security audit: config, plugin origins, sessions, network exposure — read-only redac
↓ 0
github:omdsh-dev/sandbox-micro
Support for the microsandbox backend.
↓ 0
github:omdsh-dev/sandbox-mxc
Microsoft cross-platform sandbox support.
↓ 0
github:omdsh-dev/sandbox-nono
Support for the nono sandbox backend.
↓ 0
github:PerryLink/dsh-skill-pack-security
Security-audit methodology skill pack plus the plugin_vet supply-chain gate: eight agent s
↓ 0
github:Qcsj777/dsh-stop-that-shit
Arms an explicit per-session scope contract from a `$stop-that-shit` directive and audits
↓ 0
github:QinpanWan/dsh-prompt-antivirus
Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments
↓ 0
github:ruanhaodong-tt/dsh-security-guard
Runtime security guard for DSH: loader import confinement, HTTP Host header validation, an
↓ 0
github:SARTHAK2511/dsh-cve-audit
Live CVE/supply-chain audit for your workspace's own project dependencies (npm/pip/go), ba
↓ 0
github:sashankh/dsh-taintguard
Taints the agent when tool results carry untrusted content, gates the privileged calls tha
↓ 0
github:SeaOf0/dsh-redteam-model
Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code au
↓ 0
github:Shiyuedong-Jade/DM-security
Run a read-only security assessment of a Dameng DM8 database with 60 checks and produce an
↓ 0
github:ylwl1997/noatmark-dsh-plugin
Text hygiene as a dsh plugin: sanitize untrusted text, scan invisible characters, clean LL
↓ 0
github:simon300000/dsh-auto
Adds an Auto Approve permission preset to the Web UI, using a fresh restricted Reviewer Ag
↓ 0
github:sujingkpo/dsh-auto-pass
A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web
↓ 0
github:tancheng33/dsh-code-runtime-container
Container-isolated backend for the `ctx.codeRuntime` seam: each Code Mode program runs in
↓ 0
github:tancheng33/dsh-credentials-vault
HashiCorp Vault backend for the credential seam: KV v2/v1, AppRole machine auth, per-opera
↓ 0
github:tancheng33/dsh-egress-guard
Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress al
↓ 0
github:taxueseek/dsh-plugin-guard
Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock
↓ 0
github:uwu9039/dsh-airbag
Blocks API keys pasted into the composer or written by tools, logs leak events, and scans
↓ 0
github:Vladimir-Kryshchenko/dsh-route-fence-linter
Audits every plugin HTTP route in a profile for a browser-trust fence: plugin routes win t
↓ 0
github:weisofns/dsh-security-guard
DSH plugin security guard: 28-rule static scanner, risk scoring, whitelist/blacklist polic
↓ 0
github:wld12314/agent-web-sandbox
Sanitizes fetched pages before the model reads them: strips hidden text, offsite images an
↓ 0
github:Wldpm/dsh-fileguard
Security plugin that intercepts file deletion and write commands, requiring user token aut
↓ 0
github:WyattJHayes/dsh-feishu-channel
Security-focused Feishu (Lark) channel for DeepSeek Harness: allowlisted remote-agent acce
↓ 0
github:wzn16/dsh-fs-allowlist
Approval-free writes into whitelisted directories — wraps the filesystem fence for write/e
↓ 0
github:xevil3301/dsh-chatlock
Session password lock plus an encrypted directory vault for DeepSeek Harness.
↓ 0
github:xiangshu2026/dsh-alpha-guard
Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-p
↓ 0
github:XiaoSHang05/dsh-rice-guard
Watches a turn's thinking and output streams and cancels the turn when the model starts re
↓ 0
github:Xieddenv/dsh-brain-kit
A hard hat for AI coding: graded writes (L0 read-only / L1 workspace-only / L2 full) put p
↓ 0
github:xiezouqu12/dsh-info-records
Encrypted local credential vault for DeepSeek Harness: sidebar record management, an info_
↓ 0
github:xtd1145/dsh-full-access-switch
One-time Full access switch for DeepSeek Harness: new sessions (workspaces and conversatio
↓ 0
github:yanli-nyan/dsh-recycle-bin
Sends file deletions to the Windows Recycle Bin, lists and restores them by id, and blocks
↓ 0
github:Yazzyk/dsh-file-shield
Blocks an agent from reading, searching, writing, or editing chosen files and directories,
↓ 0
github:yuloop/dsh-secret-vault
Hands secrets and PII to the agent without them entering its context, with checksum-valida
↓ 0
github:yunling-bionic/dsh-rule-guard
Reviews side-effecting tool calls against the project rules and the current goal before th
↓ 0
github:Yuuz12/dsh-webui-auth
WebUI authentication enforced at the HTTP/transport layer: four-layer login gate (resource
↓ 0
github:yyfdfsyyf-source/dsh-hard-gate
An independent permission gate above the built-in sandbox. It blocks writes outside the wo
↓ 0
github:yyjsdsg/dsh-redact
Mask secrets, local paths, private IPs, emails and phone numbers in session text before yo
↓ 0
github:yzxxy010/dsh-workspace-write-plus
Adds a workspace-write++ permission that keeps file tools inside the workspace while skipp
↓ 0
github:ZeroClave/zeroclave-dsh-privacy
Detect and redact sensitive message text before sending it to models, with local regex, br
↓ 0
github:zimai233/dsh-figma-to-lottie
Compile SVG paths and keyframe specs into self-contained Lottie JSON animation files.
↓ 0
github:ZiYuan258/dsh-mcp-control
Panel for MCP servers registered by @deepseek-ai/dsh-mcp-client: toggle each server on or
↓ 0
github:ziz12138/dsh-lawcorpus
Law paper writing corpus for DeepSeek Harness: 850 bibliographic records from four CLSCI j
↓ 0
github:ZRui-C/dsh-computer-use
Text-first computer use for DSH: background Chromium control via Playwright/CDP plus acces
↓ 0
github:zxmqq1234/dsh-auto-retry
Adds supplemental request retries, turn auto-continue and a no-response watchdog on top of
↓ 0
github:zz12hui/dsh-bili-video-summary
Windows only. Bilibili video summarizer: downloads the audio track, transcribes it locally
↓ 0
github:zz12hui/dsh-deai-audit
Audits Chinese copy for AI-sounding phrasing: a 0-100 score over six dimensions, sentence-
↓ 0
github:173787247/dsh-device-bridge
Generic Companion-protocol bridge from DeepSeek Harness to phones/IoT/legacy agents (inclu
↓ 0
github:173787247/dsh-mac-companion
DeepSeek Harness to macOS companion daemon (notify / Shortcuts / clipboard read-write).
↓ 0
github:173787247/dsh-remote-ssh
Allowlisted SSH into Unix/AIX/macOS from DeepSeek Harness (no shell; read-only by default)
↓ 0
github:173787247/dsh-wsl-fetch
Registers a wsl-proxy ctx.web fetch provider so official web_fetch uses undici ProxyAgent
↓ 0
github:173787247/dsh-wsl-git
Capped Git status / diff --stat / log --oneline (no full patches).
↓ 0
github:173787247/dsh-wsl-github
Uses a GitHub App to report open PRs and the latest Actions run for the current repo witho
↓ 0
github:173787247/dsh-wsl-glab
Read-only glab MR / issue / ci status.
↓ 0
github:173787247/dsh-wsl-gpu
Probes nvidia-smi and GPU visibility inside WSL.
↓ 0
github:173787247/dsh-wsl-helm
Read-only Helm list / status / history.
↓ 0
github:173787247/dsh-wsl-hostsvc
Probes Windows-host Ollama, LM Studio, vLLM, and llama-server from WSL, compares ctx, and
↓ 0
github:173787247/dsh-wsl-im
Bridges Feishu, WeCom, DingTalk, QQ, Slack, Discord, Telegram and Mattermost into dsh agen
↓ 0
github:173787247/dsh-wsl-jev
Call TypeSafe Jev / OpenRouter System One for noul, choice, and score (jev_ask / jev_check
↓ 0
github:173787247/dsh-wsl-k8s
Read-only kubectl get / describe / logs / contexts for dsh on WSL (configurable log tail).
↓ 0