gqallen931
DeepSeek Harness plugin for the Paper-gogo evidence-first paper workflow: 18 Phases, G0-G6 gates and four-state evidence audit as native tools, with the workflow and 57 skills bundled in.
bailong-Hakuryu
DeepSeek Harness 策略驱动的仓库安全评估插件,支持包生命周期评估、证据、发现、裁决、导出和 /security 指令。 | Policy-driven repository security assurance plugin for DeepSeek Harness with package lifecycle assessments, evidence, findings, verdicts, exports, and /security routing.
john-walks-slow
Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.
azazo1
按单命令前缀自动放行 DSH 沙箱提权请求, 含管道与链式的命令一律转人工审批.
Jannchie
Claude-Code-style artifacts for DeepSeek Harness: an artifact tool, an authoring skill, and an in-app sandboxed HTML browser
STARDUSTLC666
DSH 代码安全审查插件:40+ 确定性规则与密钥熵检测,支持 git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite。
evanfang0054
为 DeepSeek Harness 提供基于 Tailscale 的安全远程访问运营面板:一键健康检查、HTTPS 入口开关、macOS 代理绕过、中继服务器运维、ACL 生成。Tailscale remote-access control panel for DeepSeek Harness: health checks, HTTPS serve toggle, proxy bypass, relay ops, ACL helper.
JohnXu22786
Database connector bundle for DeepSeek Harness (dsh): SQLite/PostgreSQL/MySQL connections, schema introspection, read-only safety, a write approval gate and a JSONL SQL audit trail.
DWJZ
按路径与能力(read/write/create/delete/execute)授予 DSH shell 调用的文件权限,并在进程真正运行其下的 macOS Seatbelt profile 里强制;会话里的「审批」标签页显示每次判定是规则、自动复核还是人拍的板。 / Filesystem permissions for DSH shell calls, granted per path and capability instead of per command name, enforced in the process sandbox, with an Approvals tab showing which layer decided each call.
liuwenji007
Static capability disclosure for DeepSeek Harness plugins — evidence-backed, zero-token, no safety claims.
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.
173787247
Sandboxed jq / yq / read-only sqlite3.
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.
mikasa-servent
Deliverable evidence-chain & conformance checks for DSH — turn requirements into an executable spec, trace every number to a provenance ledger, audit PDF/OOXML metadata and archive manifests. MCP-ready.
tancheng33
Runtime security gate for DeepSeek Harness: egress host allowlist, secret redaction in tool results, and an append-only audit log
Smallballoons01
中国法定退休年龄与养老金测算:2025 渐进式延迟退休、退休倒计时、预计月养老金 —— 单文件网页计算器 + DeepSeek Harness 插件 + 跨工具 Agent Skill
hoyyang
Ponytail lazy-senior-dev ruleset for DeepSeek Harness: 7-rung minimal-code ladder, six skills (review/audit/debt/gain/help), /ponytail session command, optional always-on injection. MIT, upstream unmodified.
gtbwpkwjnb-alt
Skills Audit — 技能审查·画像·评分·优化 / Universal agent tool auditor — profile, score, optimize
Yazzyk
DeepSeek Harness (dsh) 插件:在 Web GUI 里点选文件或目录,屏蔽 agent 对它们的读取、搜索、写入与编辑,使机密内容与敏感词不进入对话(含敏感词导致请求 400 的场景)。Blocks an agent from reading/searching/writing/editing chosen files, keeping their contents out of the conversation.
iimaguest
DeepSeek Harness plugin: stops the sandbox escalation fields being advertised to a model when the calling session cannot grant them, fixing the retry loop known models fall into at danger-full-access.
axelfreeman
🔒 12-method security audit for Hermes Agent — virus scan, rootkit detection, SSH brute force protection
liyixuan201211
DSH plugin: lock, verify and govern AI agent skills. Tells you what a skill can do before you install it — and when it silently gains a capability after your review. Ships no boot-time code.
liyixuan201211
What can this MCP server actually do — and has it changed since you trusted it? Inspect its declared capabilities, seal them in a lock file, and get told when a later version can do more. Never invokes a tool; gives the server a minimal environment.
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