Best DSH Sandbox Plugins

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

Maintained fork of dsh-approval-gate. A neutral operation whose confirmation count has reached the threshold auto-approves when the judge is unavailable, instead of prompting a human again; approver-facing explanations are generated in Chinese from the real sandbox mode, command and paths. Also carries deterministic hard-deny for credential exfiltration and system-path destruction, judge-input redaction, a judge model candidate chain, fingerprint-scoped allow rules, and an approval view with unified diff and one-click revert.

Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.

OpenAI Codex CLI wrapper: one-shot exec, repo review and session resume with a default read-only sandbox.

A web Settings "Loop engine" switch that swaps the agent loop driving every dsh session among five engines — the built-in in-process loop plus hosted Claude Code, Codex, Pi, and Kimi Code — with zero changes to the harness; each hosted engine keeps its thinking and tool calls in the durable session transcript, takes over commands, skills, and the agent preset, and runs sandboxed through the dsh subprocess seam.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.

Gives DeepSeek Harness control of the Tabbit Browser: auto-loads the tabbit-browser skill on install, detects official Tabbit and Tabbit Browser releases (>= 1.9.0), checks the tabbit-cli persistent runtime, diagnoses the per-platform DSH sandbox mode needed to call the CLI, and downloads the region-matched official installer via a background job when no qualifying version is present.

Gives DeepSeek Harness control of the Tabbit Browser: auto-loads the tabbit-browser skill on install, detects official Tabbit and Tabbit Browser releases (>= 1.9.0), checks the tabbit-cli persistent runtime, diagnoses the per-platform DSH sandbox mode needed to call the CLI, and downloads the region-matched official installer via a background job when no qualifying version is present.

dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)

Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

Replaces the web profile's pwsh shell executor with a subclass that rewrites every command through `rtk rewrite` before execution for token savings, running the original command unchanged on any rewrite failure (no equivalent, missing rtk, timeout) and keeping sandbox semantics intact.

Zero-config per-turn git checkpoints: after every completed agent turn in a git workspace, stages all changes into one tagged \[turnsnap] commit (serialized queue, sandbox-policy aware), so any turn is a rollback point.

Sandboxed ripgrep / fd / ast-grep under allowRoots (defaults include ~/.dsh/im-workspace).

Approval-free writes into whitelisted directories — wraps the filesystem fence for write/edit tools and auto-answers bash sandbox escalations that touch whitelisted paths, with a settings GUI.

Adds a workspace-write++ permission that keeps file tools inside the workspace while skipping the Windows process sandbox for wildcard-allowlisted executables such as Git Bash.

IDE workbench plugin for DSH. Fast terminal (restty/WebGPU over a Rust PTY), CodeMirror 6 editor, file explorer, markdown notes, sandboxed browser, and ripgrep search — all as tabs in dockable right and bottom panels. Extendable with your own React components.

Sandboxed jq / yq / read-only sqlite3.

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Approval-free writes into whitelisted directories — wraps the filesystem fence for write/edit tools and auto-answers bash sandbox escalations that touch whitelisted paths, with a settings GUI.

Workspace-scoped Semgrep SAST tool for DeepSeek Harness with a managed Windows x64 runtime, structured bounded findings, cancellation and timeout controls, and user-approved sandbox escalation. Installs from npm as @aaub-software/dsh-semgrep-sast.

Diagnoses and repairs DeepSeek Harness on native Windows around the official persistent PowerShell and Workspace Write stack, creates the desktop shortcut, and keeps earlier Git Bash and BusyBox presets behind an explicit legacy setup. No WSL.

Use your DSH models in [Libre WebUI](https://github.com/libre-webui/libre-webui) for chat, sandboxed Work and usage tracking, with provider credentials kept in DSH. Requires Libre WebUI 0.37.0 or later.

Support for the nono sandbox backend.

Support for the microsandbox backend.

Zero-dependency verification standard for DeepSeek Harness (dsh) plugins — static structure gates (R), cordis contract checks (K), sandbox smoke (D), ecosystem-listing checks (CC). 零依赖 DSH 插件核验标准：静态结构门禁、cordis 契约扫描、无头沙箱冒烟与生态收录核验。

Uses an isolated LLM review to approve or reject DSH sandbox permission requests.

Runtime security guard for DSH: loader import confinement, HTTP Host header validation, and source patch for VM sandbox escapes (4 CVEs). AI-assisted.

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

Microsoft cross-platform sandbox support.