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

31 个项目,匹配「risk」

开发工具 技能

brooks-lint

hyhmrright

AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix

agent-skills ai-code-review architecture-review auto-fix
安全与治理 插件

api-relay-audit

toby-bridges

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

ai-agents ai-audit ai-security anthropic
其他 技能

Systematically clarify intent, challenge assumptions, resolve contradictions, and align goals, constraints, risks, and success criteria.

agent-skill deepseek-harness dsh-plugin
其他 待识别

DSH plugin: Claude-style Chinese risk control & conversation autonomy for DeepSeek Harness web

deepseek-harness dsh dsh-plugin
生活娱乐 插件

dsh-quant

pengpengyi92

"🐳 Dsh-Quant: The Everything-Plugin Ai native Quant OS "

ai-agents algorithmic-trading backtesting deepseek
其他 待识别

Delete DeepSeek Harness sessions from the UI: header danger button + sidebar session-row menu item (no conversation jump), risk-consent dialog with session name/id, stops running agents first, in-place list refresh without page reload. Works in web and the desktop client.

deepseek-harness dsh dsh-plugin
Agent 与会话 技能

agent-handoff-skill

WeirdSky924

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

agent-handoff agent-skills claude-code codex
安全与治理 插件

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

agent-harness agentic-ai ai-agents ai-safety
其他 插件

DeepSeek Harness plugin for rule-gated automatic sandbox approval with optional LLM review, one-time grants, fixed high-risk checks, and native human fallback.

cordis deepseek-harness dsh dsh-plugin
生活娱乐 技能

clawock

KCNyu

AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision workflow into your own agent: OpenClaw, Claude Code, Codex, or DeepSeek Harness.

agent-skills agentic-ai ai-agents algorithmic-trading
其他 技能

risk-rule-design

pypcfx-glitch

Rule mining for data risk control, distilled from the ideas of the "100-Day Risk Control Expert" course

agent-skill deepseek-harness dsh-plugin finance-risk-analysis
其他 插件

weiwen-law-dsh

Shaky77

唯稳律 (Weiwen's Law) 白箱风控 DSH 插件 — DeepSeek Harness 因果约束中间件

ai causality dsh-plugin harness
其他 待识别

DeepSeek Harness plugin to manage network proxy (system / manual / direct) with a live settings UI. [dsh-plugin]

dsh-plugin
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
文件与数据 插件

dsh-finance

zhang787jun

Finance and accounting workflows for DeepSeek Harness, adapted from Anthropic Finance

accounting deepseek-harness dsh-plugin finance
文件与数据 插件

Finance data toolkit for DeepSeek Harness agents: number/currency formatting (incl. Chinese wan/yi units), return & CAGR math, valuation and profitability ratios, PV/FV, risk metrics, and a data-quality checklist

cordis data deepseek-harness dsh-plugin
其他 待识别

Delete sessions from the DSH Web sidebar: a Delete action in the session menu with a risk-consent dialog; removes the log, workspace accounting and live session state.

dsh-plugin
其他 待识别

cloudq-for-dsh

TencentCloud

CloudQ integration for DeepSeek Harness, providing multi-cloud architecture governance, AIOps, risk inspection, usage, artifacts, and architecture views.

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
开发工具 技能

Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH, Claude Code, Codex, and Pi, plus a host-agnostic SOFT skill with ADAPTIVE adapter guidance.

ai-agent claude-code-plugin claude-code-skill codex-plugin
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
其他 插件

dsh-ios-app

kriskwok

一款可以远程控制DSH和Hermes等AI助手的APP,仅支持iOS。

deepseek-harness dsh dsh-plugin dsh-plugin-market
模型与 MCP 技能

DeepSeek Harness 多源能力发现、排序与风险检查|Multi-source capability discovery, ranking, and risk inspection for plugins, skills, MCP servers, and agents.

agent-skill capability-discovery deepseek-harness dsh-plugin
开发工具 插件

dsh-vps-manager

AIcivilization

VPS & SSH manager plugin for DeepSeek Harness (DSH): zero-token /vps- commands, an in-conversation web terminal, and AI server ops with risk-tiered confirmation. 在 DSH 里像 SSH 一样无感地用 VPS:零 token 命令、对话内终端、AI 分级确认运维。

ai ai-agent ai-agents deepseek