A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

DSH crash-rescue plugin: undo config & plugin-code changes, secret-safe snapshots, one-click SAFE MODE, plus offline CLI/GUI that work even when DSH won't boot.

DSH plugin - framework upgrade safety & plugin gating: contract pre-check, rollback point, auto-rollback on failure, evidence-based auto-disable; plus a multi-source plugin market. Unofficial. | DSH 插件：框架升级安全 + 插件门控——升级前契约预检、回滚点、失败自动回滚、有确证证据才自动禁用；另带多源插件市场。非官方社区项目。

Google Antigravity (agy CLI) models for DeepSeek Harness — streaming chat, thinking, tool activity, usage, in-GUI Google OAuth login

DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.

Login gate for DeepSeek Harness (dsh) web instances: password or shared-token sign-in, optional TOTP two-factor, session cookies, rate limiting, self-service password change and a user-management CLI

Google Antigravity (agy) OAuth auth + model access plugin for DeepSeek Harness: multi-account pool, 429 rotation, device fingerprinting, CLI and web login.

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

掌上 dsh — the standalone mobile surface for the dsh web GUI: scan-to-pair device trust, the /m/ phone UI, the /m/api RPC channel with realtime SSE mux bridge, and a polished desktop pairing panel. Extracted from dsh-remote-web-ui (M1, behavior-identical)

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.