Query and manage JumpServer through conversation: assets, users, accounts, permissions, sessions, command audit logs, command filters, and RBAC roles, authenticated with an AccessKeyID/AccessKeySecret

by SodaZheng

Add an access-verification step for DeepSeek Harness, under your control. An access-verification step for DeepSeek Harness, under your control.

by wangxing-git

DeepSeek Harness Workspace Management Toolset: view, create, register, rename, and delete workspace records (pure registration, without touching disk directories); destructive operations (delete registration, change registration path) require user approval with fail-closed behavior.

by lyaoliu

DeepSeek Harness Automated Approval Decision Pipeline: routine sandbox boundary violations are auto-approved, while dangerous, uncertain, or failed cases are all routed to manual review (fail-safe); constrained learning can be cleared with one click; includes tiered configuration UI and a block-level rollback review view. A hardened version forked from dsh-approval-gate.

by LWLAymh

File-change diff bar with keep/undo summary, plus dangerous-command approval and red highlighting for bash/pwsh.

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

by 782042369

DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.

by tancheng33

HashiCorp Vault backend for the DeepSeek Harness credential seam: central secrets, AppRole machine auth, rotation without restart, and no long-lived provider key on the agent host

String-matches tool-call input arguments, blocks dangerous tool calls (deny) or allows them with an injected warning (warn), and ships a full rules-management panel.

by nicecx

Auto-approval agent for DSH permission requests: rule layer (denyAlways/allowlist) plus Hermes Pro semantic adjudication with quick-fail retries, fail-closed to human when Hermes is unavailable, rejec

by jwilson411

DeepSeek Harness plugin: OpenAI-compat server protocol card (loopback probe, no GGUF)

DSH plugin security guard: 28-rule static scanner, risk scoring, whitelist/blacklist policy, local web dashboard and in-DSH risk popups.

Static and runtime security guard for dsh: rule-based scans for malicious code, prompt injection and token waste, runtime interception of dangerous tool calls, /scan command, plugin_scan tool, web pan

Permission guard for DSH: four scopes with read/write/execute bits in the native permission menu, plus an optional Jev semantic classifier for bash commands.

by Yukari316

Fixed an issue where the toolcall JSON schema was incorrectly parsed when using a custom provider model in DSH, which caused a continuous stream of erroneous toolcalls, and added the ability to skip long-waiting toolcalls.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Pre-execution guard: a `tools.guard` predicate decides allow, ask or refuse per permission preset for dangerous shell commands (git hook bypass, catastrophic `rm`, download-and-run, git history rewrit

by loonylabs-dev

DSH plugin that prices an automatic context rewrite before it lands and asks first — the cold re-read, in k tokens.

Transport-level authentication gate for the DeepSeek Harness Web GUI with server-side sessions, HttpOnly cookies, IP-based login throttling, and an scrypt password CLI.

by Top-Celestial-Company-Ltd

⚡ DROS™ VajraClaw for DSH: Deterministic Runtime Execution Governance & Security Circuit-Breaker Plugin

DSH Desktop plugin safety guard: self-repairs plugin load crashes and runs 8 core safety checks (2 optional: deep-config & smoke), prompting you when a plugin changes. Non-commercial source-available.

by liuwenji007

Static capability disclosure for DeepSeek Harness plugins — evidence-backed, zero-token, no safety claims.

by zhang8019

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations,

by LiHeng99

A DSH client for the StarBridge (Xingqiao) gateway — supports sign-in via address or platform account, and provides chat / feedback / knowledge-base tools and Web UI panels. Bundled without any pre-configured gateway address.