安全与治理
技能
DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.
agent
ai
ai-agents
aisecurity
安全与治理
索引目录
DSH plugin - framework upgrade safety & plugin gating: contract pre-check, rollback point, auto-rollback on failure, evidence-based auto-disable; plus a multi-source plugin market. Unofficial. | DSH 插件：框架升级安全 + 插件门控——升级前契约预检、回滚点、失败自动回滚、有确证证据才自动禁用；另带多源插件市场。非官方社区项目。
ai-empower
cli
deepseek-harness
dsh
安全与治理
插件
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
agents
ai-safety
ai-security
dsh-plugin
安全与治理
索引目录
AI agents for pentesting, code audit, fuzzing, vulnerability discovery, and reverse engineering — harnesses, sandboxes, security MCP servers, benchmarks, and evals.
agentic-ai
ai-agents
ai-hacking
ai-pentesting
安全与治理
插件
该仓库暂未提供项目说明。
dsh-plugin
dsh-plugin-market
dsh-plugins
security-audit
安全与治理
插件
Per-edit approval gate for DeepSeek Harness — red/green line diff review before write/edit/stream operations · DSH 插件：逐操作审批门，write/edit/stream 执行前进行红绿行级 diff 审查
approval
client-plugin
code-review
cordis
安全与治理
插件
多文件夹 workspace：让 DSH（DeepSeek Harness）的 Agent 不只能读写主目录，还能同时读写你添加的其他文件夹。Multi-folder workspace for DeepSeek Harness: let the agent read and write several folders at once, not just the primary one.
bwrap
cordis
deepseek-harness
dsh
安全与治理
索引目录
DeepSeek Harness 插件市场：精选目录 + GitHub 实时浏览、中英翻译搜索、安装前静态安全审计闸门。Plugin market for DeepSeek Harness with a pre-install security audit gate.
deepseek-harness
dsh-plugin
marketplace
plugin-market
安全与治理
插件
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
cordis
deepseek-harness
dsh
dsh-plugin
安全与治理
技能
⚖️ 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.
benchmark
claude-code
code-audit
codex
安全与治理
插件
DeepSeek Harness 审批守护者：权限请求先由审查模型裁决。内置 System One 决策 API 后端（TypeSafe Jev / 硅基流动 systemone / 自部署 Laya）、onLowConfidence 低置信度策略与 allowRules 免审白名单。fork 自 gbthui/dsh-auto-review。
ai-agent
approval
auto-review
cordis
