DSH-PLUGIN STORE / LIVE CATALOG

DSH插件商店

聚合 GitHub 上的 DSH 插件,打造 DeepSeek Harness 生态的一站式目录。

已收录
6553
功能分类
11
更新时间
10/07 02:01

83 个项目,匹配「ai」

安全与治理 技能

ghidra-skill-for-dsh

Cristallin2006

Custom-built for dsh (DeepSeek Harness): persistent Ghidra headless daemon + reverse-engineering agent skills (triage/unpack/decompile/pwn/pcap/APK) with circuit breakers against agent failure loops. 为 dsh 深度定制:会熔断、能从复盘进化的逆向 skill 家族。

agent-skills ai-agent android-reverse-engineering binary-analysis
安全与治理 插件

dshscan

shaoshi20

Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.

ai-security dsh dsh-plugin scanner
安全与治理 技能

seo-toolkit

Haniubub

The SEO audit toolkit built for DeepSeek Harness (DSH) — runs locally, no Claude Code, no API key required. Self-contained port of claude-seo v2.2.5: 53 Python scripts + 24 sub-skills + 18 agents, weighted score, gated fan-out, schema.org, E-E-A-T, GBP, GEO/AI Overviews.

claude-code claude-skills deep-seek-plugin deepseek-harness
安全与治理 插件

dsh-riskproof

onlyqzq

Risk-aware approval layer for high-risk AI Agent tool calls

agent-security dsh-plugin provenance tool-security
安全与治理 插件

dsh-automode

log-li

Claude Code-style auto approval layer for DeepSeek Harness: deterministic rules + two-stage classifier, circuit breaker, fail-to-human. Shadow mode day one.

auto-approval deepseek-harness dsh-plugin
安全与治理 基础设施

dsh-tensorlake-sandbox

tensorlakeai

A deepseek harness plugin for tensorlake sandbox

ai-agents ai-infrastructure deepseek deepseek-harness
安全与治理 基础设施

dsh-xray

unStone

X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.

agent-security ai-agents ai-security capability-analysis
安全与治理 插件

🛡️ 给 DeepSeek Harness 插件拍 X 光 — 插件安全体检与健康检查。只读静态扫描:代码执行/凭据/外传/混淆/安装脚本/bundle 清单,0-100 风险分。DSH tool plugin + standalone CLI。

deepseek-harness dsh-plugin scanner security
安全与治理 插件

Caushell

fatmo666

Compiler-style pre-execution safety analysis for Harness shell actions.

ai-agent bash claude-code claude-code-plugin
安全与治理 插件

Detect & break thinking-chain loops in DSH agents at the turn boundary (no proxy). Ported from ollama-loop-guard.

agent cordis deepseek deepseek-harness
安全与治理 技能

该仓库暂未提供项目说明。

agent-skills claude-code codex-cli ctf
安全与治理 插件

dsh-podman

Exagone313

Podman-backed execution for DeepSeek Harness (dsh)

containerization docker dsh dsh-plugin
安全与治理 插件

PSA-core

SiliconPsycheLabs

PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.

ai-safety dsh-plugin llm-agents machine-psychiatry
安全与治理 插件

Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.

audit dsh dsh-plugin dsh-plugins
安全与治理 插件

模式匹配自动注入 steering rules,不占系统上下文 - Inject rules when needed, without wasting context. Similar to oh-my-pi's "Time-traveling stream rules", but with a very simple and compact code implementation.

cordis deepseek-harness dsh dsh-plugin
安全与治理 插件

DSH 0.1.7 Windows ACL 沙箱在非系统盘工作区下全部命令 spawn 前失败的临时修复插件——不动任何系统 ACL,恢复 workspace-write。 | Temporary fix for the DSH 0.1.7 Windows ACL sandbox failing on non-system-drive workspaces (grantWrite / SetNamedSecurityInfoW Win32 5) — restores workspace-write without touching system ACLs. 支持 DSH 0.1.7-rc.1+。

acl deepseek-harness dsh-plugin sandbox
安全与治理 插件

npm-safe-forDSH

nisconder

DeepSeek Harness plugin that checks npm packages before install — 22 supply-chain rules, deep tarball scans, CI gates, local-first.

agent-tools ai deepseek deepseek-harness
安全与治理 基础设施

Observe-only hash-chained evidence receipts for DeepSeek Harness

agent-infrastructure ai-agents audit deepseek-harness
安全与治理 插件

QuickJS/WASM-isolated workflow engine for DeepSeek Harness with bounded resource controls

agentic-ai deepseek-harness dsh-plugin quickjs
安全与治理 插件

dsh-yolo-mode

SeverusZh

dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)

approval deepseek-harness dsh dsh-plugin
安全与治理 插件

dsh-cyber-sec

cyzlmh

Authorized security-assessment profile for DeepSeek Harness: scoped network tools, container-backed shell, authorization guard, durable evidence, 21 security skills, 7 specialist subagents

deepseek-harness dsh-plugin penetration-testing security-assessment
安全与治理 插件

dsh-worlds

frozo-ai

Remote execution worlds for DeepSeek Harness: run the agent's Bash, terminals, LSP and file tools inside a container. Zero dependencies.

deepseek-harness docker dsh dsh-plugin
安全与治理 插件

Private, per-project prompt rules for DeepSeek Harness — matched by git remote/repo/path, worktree-aware, never committed to the repo

agents-md ai-agent cordis deepseek-harness
安全与治理 插件

dsh-autogate

wangxing-git

DeepSeek Harness 自动审批插件:在 workspace-write 沙箱之上叠加确定性规则 + LLM 安全审批,自动模式不放宽沙箱、fail-closed。 Safe auto-approval for DeepSeek Harness — deterministic rules + LLM review on top of the workspace-write sandbox. Auto mode without ever granting full-access.

auto-approval deepseek deepseek-harness dsh