dsh-plugin-auth-guard
Enterprise-grade Zero-Trust Authentication, LAN/Public Access Control & Security Gate Plugin for DeepSeek Harness (DSH).
398 results
Enterprise-grade Zero-Trust Authentication, LAN/Public Access Control & Security Gate Plugin for DeepSeek Harness (DSH).
Read-side SIEM forwarder for DeepSeek Harness: normalises session activity to OCSF and ships it
Approval timeout for DeepSeek Harness: when a sandbox/escalation approval is not answered within a configurable period, the request is automatically rejected instead of waiting forever.
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
AI代码审查:找出代码中的bug、安全漏洞、性能问题和风格建议
Project DeepSeek Harness tool, approval, and result facts into a bounded action lifecycle ledger.
Config drift detective for DSH: snapshots profile/plugin state on startup, records diffs, exposes a read-only history tool. Zero runtime deps, no custom events.
DeepSeek Harness 的 Tailscale 远程访问运营面板:健康检查、HTTPS 入口开关、macOS 代理绕过、中继服务器运维、ACL 片段生成。
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
Access-password gateway plugin for DeepSeek Harness Web: every request on the gateway port requires authentication (no unauthenticated surface besides the login/setup page), first visit sets the password, and it can be rotated from the dedicated Security settings page.
AgentENV execution-world bundle for DeepSeek Harness
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
Content-addressed proof for body-free DSH tool-result custody stages
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。
Fail-closed MCP tool baseline and runtime approval security for DeepSeek Harness.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
GitHub App tools for WSL dsh: hint (env file existence) + repo PR/Actions status; never dumps secrets.
Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.
Layered session permissions for DeepSeek Harness. 有效权限 = 官方 ∩ Agent ∩ 本会话;Claw 会话钉官方沙箱(只紧不松)。
Security and connection-stability overlay for DeepSeek Harness SSH workspaces
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
VulnClaw + DeepSec 桥接插件:AI 安全 CLI(授权渗透测试 / Shield 代码审计)→ dsh 工具 + 设置页安全工具台 UI
Turn DeepSeek Harness sessions into redacted, README-ready animated demos — as a local CLI or DSH plugin.
拒绝 AI 味的 UI 设计:21 主题 + 四动词(构建/audit 审计/redesign 重构/study 提取 DNA)+ 57 个 slop 测试门 + 预输出自我批评——拒绝所有 LLM 训练成的分布默认值。受 Nutlope/hallmark(25.8k★ MIT)启发。