dsh-approval-gate
DeepSeek Harness 自动审批门控:Flash 模型预判写入/命令是否不可回补,安全自动批准、危险转人工(fail-safe),最小人工介入,含人工审查 UI
313 results
DeepSeek Harness 自动审批门控:Flash 模型预判写入/命令是否不可回补,安全自动批准、危险转人工(fail-safe),最小人工介入,含人工审查 UI
Model-reviewed Auto Approve permission preset for the DeepSeek Harness Web UI
Allow, ask, or deny DeepSeek Harness tool calls before execution
Audit the DeepSeek Harness plugin list by origin (official vs self-installed): a /plugin-audit command plus a Source tab in Web Settings
Session execution analytics and audit reports for DeepSeek Harness. Understand how your agent actually worked: steps, tool calls, failures, repeated actions, token usage and verification signals.
Security-first QQ Bot channel plugin for DeepSeek Harness, built on Tencent's official SDK
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)。
Approval mode control for DeepSeek Harness: default approval (ask) or bypass approval (auto-approve every tool call), next to the permission selector. DSH 审批模式插件。
DeepSeek Harness desktop popup plugin: shows AI thinking status in a bottom-right always-on-top card, alerts on permission requests and completion, with a DeepSeek-style UI
Observe-only hash-chained evidence receipts for DeepSeek Harness
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.
DSH compatibility plugin that treats redundant non-escalating sandbox permission fields as a no-op
Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).
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.
OrbStack VM sandbox v0.4.0: 在 v0.3(安全/可靠性)基础上新增 A1 交互终端、A3 场景化一键创建、A4 删除撤销+完成通知、A5 配额一眼可见、A6 协作分组、B1 安全基线 vm_harden、B2 密钥库 vm_secret、C1 增强指标+阈值告警 vm_alert、D1 vm_scp/vm_logs/vm_env/vm_withdraw、D2 调度 UI+用量报表 vm_report、D3 导出分片/远端、D4 累计配额+创建排队。
Find and audit DeepSeek Harness (DSH) plugins inside the agent — live `dsh-plugin` topic search + source audit with trial-to-production install plans.
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
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。
DeepSeek Harness 自动审批插件:在 workspace-write 沙箱之上增加 Auto 档——确定性规则放行/拒绝,模糊操作由 LLM 裁决,危险操作转人工。保留工作区沙箱边界,不放宽为 full-access。
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
Export-copy redaction for DeepSeek Harness session telemetry
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness