플러그인

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

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

Web UI와 데스크톱 클라이언트에서 DSH 세션을 삭제합니다: 헤더의 위험 버튼과 세션 행 메뉴 항목에 위험 동의 대화상자를 제공하며, 호스트 엔드포인트와 에이전트 도구가 세션 로그, 프로젝션 캐시, 워크스페이스 계정 정보를 함께 제거합니다.

로컬 보안 감사: 설정, 플러그인 출처, 세션, 네트워크 노출을 점검하여 읽기 전용의 마스킹된 위험 보고서를 생성합니다.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

DeepSeek Harness 에이전트를 위한 두 번째 뇌입니다 — 위험한 도구 호출 전에 강력한 모델이 검토하며, 하나의 지갑으로 67개 모델을 사용할 수 있습니다. 계정도 API 키도 필요 없습니다.

현재 시장 데이터에 대한 출처 규율을 갖춘 금융 리서치 워크플로와 포트폴리오 리스크 도구

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.

Risk-gated approval automation for DeepSeek Harness: flash pre-classifies whether a write/command is irreversible — safe operations are auto-approved, dangerous ones are escalated to human approval (fail-safe).

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

Provenance-aware execution security for DeepSeek Harness. Track sensitive data across tool calls and stop risky side effects before execution.

Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.

Quality-aware in-agent plugin discovery: a find_dsh_plugins tool that ranks the whole dsh-plugin topic through a daily quality-scored index (installable manifest, curated listing, license, activity) merged with a live gh search — zero LLM API cost, risk flags and exact install commands in every result.

Read-only health clinic for the installed DSH plugin set: loader health, dependency integrity, version compatibility, install-script risk, duplicates and patch integrity, delivered as a model tool, a Settings dashboard and JSON reports.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

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

Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness

Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.

催办风险灯（Urge Risk Light）— 根据流程节点停留时间与 SLA 对比批量判定红/黄/绿催办风险的 DeepSeek Harness 工具插件，含结果卡片与右下角悬浮组件

DeepSeek Harness 高峰期模型自动切换插件：高峰前自动切到指定替代模型，高峰后切回官方模型。· Auto-switch to an alternate model before DeepSeek peak hours and back to the official model afterwards. · 本插件由 AI 全权开发，作者无编程经验，请自行测试安全性；安装说明可能含 AI 幻觉。· Developed by AI; test at your own risk; install

Zero-interruption audit and fuse blocking for DeepSeek Harness: silently records every tool call with deterministic risk scoring, cumulative-risk bonuses, risk-level breakdowns and retention-based cleanup; blocks irreversible catastrophes (protected-path deletion, disk wipe, force-push to protected branches/refs, credential exfiltration), and renders a redacted /risk-guard operation bill with --since filtering.

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Update copilot for DeepSeek Harness: one scan covers the dsh core, official bundles, and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.