@suagr_xl/dsh-safety
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.
395 results
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.
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/)
Security and connection-stability overlay for DeepSeek Harness SSH workspaces
DSH plugin bundling the remote-shell skill: secure SSH/SFTP/Telnet/WinRM remote operations with an encrypted credential vault.
Scan installed DeepSeek Harness plugins and grade stability risk (hook surface, startup work, preflight health, packaging, dependencies). 扫描已安装插件的稳定性风险(钩子面/启动任务/预检/打包/依赖)。
DSH 插件安全审查:静态扫描 + 当前会话模型语义审查 + 用户确认
Persistent credential vault for DeepSeek Harness (DSH): manage API tokens, server logins, and site credentials in one settings panel. Secrets live in the DSH credential store and are consumed by the model via vault_status / vault_get tools.
GitHub App tools for WSL dsh: hint (env file existence) + repo PR/Actions status; never dumps secrets.
DSH v0.18.x LAN access plugin: binds the web server to 0.0.0.0 (bypassing the official --host 0.0.0.0 CLI guard at the supported composition layer) and injects a browser shim that fixes the crypto.randomUUID() secure-context crash which breaks the client RPC layer on plain-HTTP non-loopback origins (phone browsers).
DSH plugin: resolve a company name to a stock symbol and fetch a live stock profile with current price, powered by SEC EDGAR and yahoo-finance2
Safe Git credential hints: GCM path, HTTPS vs SSH origin (never returns secrets).
保险区 Vault Wall — 让 DeepSeek Harness 无法感知、无法触碰用户指定敏感路径的隔离墙插件(隔离墙 + 人在回路审批 + 执行后验证 + 循环纠正 + 可回滚规则)
Git worktree-aware workspace browser for DeepSeek Harness: project sections, repository-grouped worktrees, and automatic workspace synchronization.
DeepSeek Harness 隐私保护插件:监控本地 Privacy Gateway (:8317) 与 Qwen2.5-0.5B 小模型,管理凭据脱敏、豁免白名单与加密密钥,并提供带凭据保护的模型入口与部署按钮
全局提示注入 / 上下文病毒(context virus)防御插件:tools/pre-execute 扫工具参数、tools/post-execute 扫工具结果、agent/pre-step 扫进入模型前的消息并注入金丝雀守卫、llm/stream 出站消毒;支持 block / quarantine / monitor 三模式、磁盘化可演进病毒库(学习/导入/导出)与审计日志。纯 JS 无原生依赖,profile 层挂载,对所有预设与子代理全局生效。
Adds a visible vertical scrollbar to the DSH settings navigation when its sections exceed the viewport.
DSH LangPack framework plugin for DeepSeek Harness: installable ZIP language packs with A/B/C engines, composite pipelines, terminology retrieval, secure installer, GitHub marketplace and a built-in risk disclaimer gate.
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.
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests
DeepBrain (深脑) plugin for DeepSeek Harness: give your agent an organization's second brain — judgments with evidence chains, verbatim-verified quotes, people's historical positions, and 200+ analysis methods it can borrow
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
敏感信息扫描:递归扫描代码库中的泄露密钥/令牌/私钥/硬编码密码,输出去敏感化的位置与严重级,提交前自查安全
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。