dsh-airbag
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
74 results
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
Safety-gated Windows Computer Use tools for DeepSeek Harness with ModLens visual grounding.
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.
Agent- and GUI-controlled DG-LAB Coyote e-stim plugin for DeepSeek Harness: safety-bounded strength, programmable waveforms, and a DSH-aligned web panel.
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
dsh-tmuxctl — the control plane for tmux: list, drive, capture, split, swap, run, and watch the panes you already have open, with safety by default
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
Maestro Guard — pre-execute safety gate: native DSH approval prompts, parsed command-surface rules, decision journal
Independent Codex Guardian-style approval reviewer for DSH.
Tiered auto-review for DeepSeek Harness (DSH): static-rule safety net + LLM reviewer + human fallback. Auto-approve safe actions, auto-deny irreversible ones, ask a human for the rest. PURE VIBE CODING - not audited, use at your own risk.
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn
Hard-stop DeepSeek Harness tool use after a per-session call budget.
Fifth DeepSeek Harness mode with configurable Codex, Claude Code, or DSH audits, user-approved remediation turns, progressive Cordis/skill elevation, safety pauses, and Web/TUI review controls.
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
禁止 write 覆盖已存在的文件:write 只允许创建新文件,目标已存在时在工具执行前直接拒绝并提示改用 edit,全局所有会话生效,防止模型用 write 整体覆写已有内容。纯 host 端 dsh 插件。
distro_info: structured wsl -l -v, default vs current distro, UNC path safety.
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot,扫码即用:dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.
把 DeepSeek Harness (dsh) 装进飞书/Lark 的 bot,扫码即用:dsh Web 可视化设置、流式卡片、项目工作区、并行任务、多角色 Agent、安全网守护。| Bridge DeepSeek Harness into Feishu/Lark with visual dsh Web settings, streaming cards, workspaces, parallel tasks, roles and a safety-net guardian.
Declarative Claude Code-style permission rules plus a Codex-style process-level network policy for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), workspace-path, and network-target (domain/ip/port/scheme) matching on
Unified DSH checkpoints with linked-worktree rollback, session replay, and a graphical conversation branch tree
AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.
dsh bundle for computer-control: desktop control (screen capture, pointer/keyboard injection, accessibility-tree semantic actions, safety guards) bridged to the harness over stdio JSON-RPC.
Installing-time safety gate for the DSH plugin market — scans npm / GitHub plugins before the market executes them. · DSH 插件市场安装安全检查:安装前自动检测三方插件风险,安全直接放行,有风险弹窗由你决定。
DeepSeek Harness guardrail that limits how many files an AI coding agent can edit per turn