dsh-vault-wall
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)
218 results
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)
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
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/)
DSH plugin: a codex-style apply_patch tool (*** Begin Patch / *** Update File / *** Add File / *** Delete File) injected into the model toolset through DSH's built-in sandbox, with a settings card to choose injection scope (off / GPT models only / all models).
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
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.
Standalone DeepSeek Harness access-mode plugin with Default, No Edit, and Auto modes
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Look up what a DeepSeek Harness plugin can actually do, from inside dsh.
Offline content-addressed proof for supplied license-obligation delivery closure
Codex-style Guardian reviews, audit, and manual override for DeepSeek Harness
修复 sandbox_permissions 和 justification 字段在 pwsh/bash/fs/dsh-sandbox 中的 no-op 升级报错。当会话已是 danger-full-access 模式时,模型携带空 justification 或重申同一模式被拒的问题。
DSH plugin: anonymize workspace-external file paths before model requests with user confirmation
Press Enter to approve the sandbox permission-escalation prompt in the DeepSeek Harness WebUI instead of clicking the Allow once button.
Scan project lockfiles (npm/pnpm/yarn/pip/go/cargo/maven/gradle/...) against the free OSV API and report confirmed dependency vulnerabilities with fix versions and remediation commands.
文本脱敏:把文本中的邮箱/手机号/身份证/银行卡/IP/密钥等敏感信息替换为掩码,分享前保护隐私
Container-isolated backend for the DeepSeek Harness code-execution seam: Code Mode programs run in a fresh container with no network, a read-only rootfs, and kernel-enforced memory, CPU, and pid ceilings
Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.
Password-gated Sudo access permission mode for DeepSeek Harness
DeepSeek Harness plugin: plants a canary string in model-visible context and denies any tool argument or outbound URL that echoes it back
DSH 危险命令守卫:通过 tools/pre-execute 门禁拦截 bash/pwsh 高危命令(rm -rf /、mkfs、dd 写设备、管道执行脚本、git push --force 等),支持分级策略(极高危始终拒绝 / 中危跟随全局 deny/ask/log)、用户自定义规则与白名单。
【实验性】只读安全审计模式插件(自动只读、工具级白名单、强制交付选择)· EXPERIMENTAL plugin for the read-only security audit mode (auto read-only, tool allowlist gate, mandatory delivery choice);日常使用推荐 dsh-presets 仓库的原生纯预设版。
Deterministic DeepSeek Harness Web client plugin that explains the Windows-sandbox `spawn EPERM` failure as a distinct Conversation Node.