@deepseek-ai/dsh-sandbox-nono
nono (Landlock/Seatbelt) backend for the DeepSeek Harness sandbox seam with a vendored fail-closed executor
188 results
nono (Landlock/Seatbelt) backend for the DeepSeek Harness sandbox seam with a vendored fail-closed executor
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。
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
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.
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。
DolphinDB integration for DeepSeek Harness: the WebSocket executor, the model-facing query/write tools, and the bundled DolphinDB skills as one installable profile bundle
A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.
我的Cordis 安全加固 v5(pkg-9):补全第二轮复测发现的 3 处兜底 catch 错误脱敏(/api/browse/pick、/api/installed 外层、listPlugins 枚举失败),所有错误输出统一走 safeErrorMsg。其余与 pkg-8 相同(最终安全版):信任栅栏 v2 / profile 白名单 / 无 agentId / 畸形编码 400 / browse 工作区限制 / readBody 流式解码 / 80MB / 文件名净化 / 导出假 ID 脱敏 / 导入兜底 / 打包整包。
Blaxel sandbox execution plugin for DeepSeek Harness (DSH)
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.
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
Composable three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, guarded strategies, WebUI, and headless tools.
Independent Codex Guardian-style approval reviewer for DSH.
Read-only market quotes, OHLCV history, fundamentals, news, search, and health checks for DeepSeek Harness
Vision + Android UI automation plugin for DeepSeek Harness: gpt-5.6-luna screenshot understanding and real-tap mobile app testing via adb
Diary Detective for DeepSeek Harness — a warm mirror that reads journals, illuminates blind spots, and gives gentle daily feedback. 赛博日记侦探:一面有温度的镜子,读日记、照见盲点、给温柔反馈。
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).
DeepSeek Harness 的 TencentDB Agent Memory Adapter:自动 recall、turn 捕获与只读搜索工具。
Curated Irmia DevKit tools ported to the DeepSeek Harness: safe_edit / safe_rollback / multi_edit / http_get / http_post / code_index / code_explore / code_diff_impact / db_query.
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
Let your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client
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.
Windows-friendly minimal agent preset for DeepSeek Harness: sandboxed pwsh, native cmd.exe, and str_replace_editor.
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.