dsh-request-privacy
Provider request metadata minimization extension for DeepSeek Harness
257 results
Provider request metadata minimization extension for DeepSeek Harness
Lock, verify and govern AI agent skills: a DSH plugin that makes the agent check what a skill can do before installing or updating it, and notice when it changes.
DeepSeek Harness bundle that registers the skills-summarize-audit skill pack on ctx.skills.
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
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.
DeepSeek Harness bundle for the official Wolfram/AgentTools MCP server: kernel discovery, a transparent stdio supervisor that owns only its own Wolfram process tree, and a native DSH permission policy over the Wolfram tools.
LLM auto-review approval answerer for DeepSeek Harness — decides sandbox escalations without a human prompt via a deterministic filter and a clean-context LLM safety review. REQUIRES a patched harness core (see core-patches/)
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
Seam-aligned background command execution for DeepSeek Harness — run_command via ctx.shell under the session sandbox policy, auto-promotion into ctx.jobs
DeepSeek Harness WSL plugin: pass/age secrets with allowlist; list/exists; secret_to_env without dumping values into chat.
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
DeepSeek Harness 自动审批门控 + 设置页
dsh 插件 · 用户管理:给 dsh web 加登录门禁——未登录访问弹登录/注册页,首个注册者自动成为管理员;支持 TOTP 两步验证(验证器 App 扫码/手输密钥绑定);管理员可管理所有用户(删除、重置密码、角色调整、重置两步验证)并查看登录记录与访问记录,普通用户只能查看和修改自己的信息。
Enhanced DSH workspace directory picker: cross-drive/root browsing, breadcrumb jumps, and risk/permission visual indicators
DeepSeek Harness (DSH) 插件:可逆时间旅行与审计。为工具副作用建立「前状态快照 → 执行 → 补偿」链路,提供 rewindTo(turnId) 按轮次倒序恢复工作区,内置审计规则引擎。
依赖安全审计:扫描项目依赖的已知漏洞(OSV.dev)并检测过期依赖(npm registry),返回漏洞严重级/修复版本与升级幅度
Content-addressed proof that recorded DSH authorization decisions and effects agree
安全加固:威胁建模(STRIDE)+ 三层边界系统,任何接收用户输入/鉴权/存储敏感数据/集成外部服务的功能都按安全第一开发。受 addyosmani/agent-skills(88k★ MIT)启发。
WCAG 2.2 无障碍审计:POUR 原则、合规等级、自动化+人工验证、修复建议。受 wshobson/agents(38k★ MIT)启发。
Offline-first static admission scanner for DeepSeek Harness plugins.
Session management for DeepSeek Harness (DSH): list all historical sessions in a settings page and physically delete a session's log directory (with a type-to-confirm dialog and an audit trail).
Standalone DeepSeek Harness access-mode plugin with Default, No Edit, and Auto modes
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
dsh plugins ported from eco-agent: permission gate, audit chain, memory tree