DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
24 个项目，匹配「llm」
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.
PerryLink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
KongFangXun
sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 25 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 11 plugins). Everything can be FDEing.
openguardrails
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
JUANWANG-BUAA
Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/directory support.
Ed-Marcavage
AI agents for pentesting, code audit, fuzzing, vulnerability discovery, and reverse engineering — harnesses, sandboxes, security MCP servers, benchmarks, and evals.
AskTheWay
⚡ 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
PerryLink
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
mokuyoaxis
Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.
unStone
X-ray for DeepSeek Harness plugins: declared capabilities vs actual behavior. Registry + static scanner + badges.
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.
nisconder
DeepSeek Harness plugin that checks npm packages before install — 22 supply-chain rules, deep tarball scans, CI gates, local-first.
Andy8647
Automode for DeepSeek Harness: a fourth permission preset — full access with an LLM classifier as the only gate before every tool call.
SeverusZh
dsh-yolo-mode - an LLM-powered auto-approval plugin for DeepSeek Harness sandbox escalations (built-in presets + custom permission levels, fail-closed)
cdxiaodong
该仓库暂未提供项目说明。
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.
ang-XWBWZ
AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.
Martlet-Tech
Explain what a pending dsh approval will actually do, with one LLM call: an Explain button beside Allow/Reject in the DeepSeek Harness Web GUI.
NexusClawHQ
The deny-by-default governance kernel for AI agents — permissions, L0–L4 guardrails, human approvals and an immutable audit chain as an Apache-2.0, framework-neutral library. Gate LangGraph / CrewAI / n8n / Dify or plain scripts in three lines.
XiaoYuOvO
DSH LLM response-stream injection filter: hard-block rare Unicode scripts (Track A) + score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall. Install: dsh plugin --profile web add github:XiaoYuOvO/dsh-llm-injection-filter
jhckevin
Live request metadata minimization for DeepSeek Harness, covering the native DeepSeek provider with WebUI settings.
lxwallac
DSH (DeepSeek Harness) plugin that hides or blocks sensitive filesystem paths from AI agents — privacy, sandboxing, guardrails & human-in-the-loop approval for Node.js
mtdx2001
让 AI 的英文推理流实时变中文：75,353 句 DeepSeek 精修库随包、本地 1.8B 实时 + 7B 空闲校正的三层质量、OpenAI 兼容端点一键接入，数据不出你的显卡。MIT，附 22 条踩坑实录的智能体自举手册。
slow-stack
⚖️ The audit AI coding agents can't skip — deterministic facts (git history, test coverage) and six-gate claim adjudication for code security audits. Not another scanner.