treg-dsh
OpenRouter for tools - 2,896 agent-friendly tools, pay for the usage, not subscription
35 results
OpenRouter for tools - 2,896 agent-friendly tools, pay for the usage, not subscription
DeepSeek Harness plugin for remote access: a token-gated reverse proxy keeps settings, credentials, and file access working over public tunnels and on other devices instead of returning 403. Per-device sessions.
Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.
DSH 社区插件生态指南 + 两个审计工具:注册「dsh-community-plugins」skill,让每个会话都知道如何发现、评估、安装社区插件;注册离线工具 dsh_plugin_audit,把已装插件的 bundle 层完整性、peer 区间、官方包的具名导出、slot 契约与服务注入逐条比对到本机 dsh 构建;注册联网工具 dsh_plugin_inspect,在安装前下载 tarball、校验 integrity、在临时目录里审计后删除,不安装、不执行 lifecycle 脚本。只提供方法与事实,不推荐任何第三方插件或市场。轻量:纯 JavaScript、单一依赖、无构建步骤。
Security-first QQ Bot channel plugin for DeepSeek Harness, built on Tencent's official SDK
CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode native integration.
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
AI approval answerer using the unified ctx.llm route with fail-closed local policy checks
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
Seatbelt (libsandbox) sandbox provider for the DeepSeek Harness sandbox seam on macOS: a cordis plugin that replaces @deepseek-ai/dsh-sandbox-local's seatbelt rung via a prebuilt seatbelt-run launcher — no dsh source changes, no PR required
NeevSandbox execution providers for DeepSeek Harness
DSH 插件安检机 — install-time static security auditor for DeepSeek Harness plugin bundles. Zero dependencies, zero install scripts, zero build step.
Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules (31 high/24 medium/5 low) scan plugin sources for malicious install scripts, credential theft, obfuscation, persistence and network callbacks before 'dsh plugin add', plus 12 destructive-command patterns and workspace-boundary checks against accidental deletion. | 安装安全闸门与数据保护闸:60 条静态签名规则(31 高危/24 中危/5 低危)扫描插件恶意行为、持久化与外传,12 种危险命令模式与边界检查拦截误删。
Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
Project DeepSeek Harness tool, approval, and result facts into a bounded action lifecycle ledger.
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
A fail-closed, auditable approval policy plugin for DeepSeek Harness
Deterministic DeepSeek Harness Web client plugin that explains the Windows-sandbox `spawn EPERM` failure as a distinct Conversation Node.
Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.
Multi-root Workspace for DeepSeek Harness: adds N additional roots to the workspace sandbox scope as an out-of-tree bundle
Localize leftover DSH UI chrome to Chinese (command palette descriptions, permission presets, reasoning effort) at the display layer, and detect when the official build adapts them