dsh-sandbox
DSH 测试沙盒插件:把开发/测试任务路由到进程级隔离的沙盒实例(独立进程 + 独立 DSH_HOME + 独立端口),提供创建/注入/运行/健康检查/停止/销毁/清理与门禁式合回等原生工具,全程零影响本体(3080)。
173 results
DSH 测试沙盒插件:把开发/测试任务路由到进程级隔离的沙盒实例(独立进程 + 独立 DSH_HOME + 独立端口),提供创建/注入/运行/健康检查/停止/销毁/清理与门禁式合回等原生工具,全程零影响本体(3080)。
DeepSeek Harness 权限规则引擎:hard/deny/ask/allow 四级规则(hard 高于全访问)、全局与 workspace 作用域、通配符路径保护、可视化草稿式编辑器,规则持久化于自管 JSON
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.
DSH bundle: grok-geo GEO brand audit agent skill — AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/Gemini/豆包/DeepSeek/Kimi/文心一言...), shipped as a bundled skill provider. Zero-dependency.
Audit the DeepSeek Harness plugin list by origin (official vs self-installed): a /plugin-audit command plus a Source tab in Web Settings
DSH Web UI 认证网关:登录保护全部 HTTP/WS 接口;用户管理、邀请码注册、TOTP 两步验证与通行密钥(Passkey/WebAuthn)登录。
DeepSeek Harness 的 Docker 容器沙箱部署级插件(与 dsh-plugin-vm-sandbox 全能力对齐):39 个 docker_* 模型工具、快照/回滚、文件传输、端口转发、后台任务、审计、共享/配额/回收、网络策略、多容器并行执行与华丽原生 UI。无需 OrbStack,Linux/Windows/macOS 均可使用。
dsh-yolo-mode —— DeepSeek Harness 双面包插件:当会话处于可写沙箱模式且审批策略为 ask 时,用大模型自动裁决沙箱升权申请,支持内置预设与自定义权限层级,并提供宿主 settings + 自发布设置桥(/yolo-mode)与 Web 客户端 UI。
🐳 The Everything-Plugin Quant OS — AI-native & DSH-native: 46 tools, 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET pipeline. Methods open, secrets internal.
Audit deepseek-harness (DSH) plugins before install, guard them at runtime. Static verdict + pre-install audit protocol; supply-chain checks (typosquat, OSV); exfiltration & ransomware detection, honeypot canaries, integrity baseline. Alarm-only; blocks confirmed destructive ops.
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
Windows Git Bash fix for DeepSeek Harness (dsh): MSYS sandbox conflict + terminal inspector, plus the minimal-win collective-thinking preset (we/let's reasoning chain).
nono (Landlock/Seatbelt) backend for the DeepSeek Harness sandbox seam with a vendored fail-closed executor
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板
Real-time attention alerts for DeepSeek Harness: a global banner plus flashing workspace entries when the agent is blocked (approval request / sandbox denial), with an audible chime and OS-level notifications for new blockers.
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
Blaxel sandbox execution plugin for DeepSeek Harness (DSH)
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
Find and audit DeepSeek Harness (DSH) plugins inside the agent — live `dsh-plugin` topic search + source audit with trial-to-production install plans.
KISS's Law (Weiwen's Law) universal causal engine (white-box presentation). DeepSeek Harness (Cordis) plugin implementation.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
DSH security audit plugin: find, validate, and report vulnerabilities (equivalent rebuild of codex-security methodology, skills + workflow capsules only).
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板