by Fisfzy · Agent Tool · ★ 221
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 221 |
| Forks | 37 |
| Language | JavaScript |
| Category | Agent Tool |
| Quality Score | 59/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-28 |
| Created | 2026-08-07 |
| Platforms | browser, node |
| Est. Tokens | ~16k |
ego-browser — 看得见的 Agent 浏览器 = 0.1.2-rc.1" = 0.12.2 (optional)" = 22" 仓库：｜版本历史见 CHANGELOG.md｜详情页：dshfind 版本兼容矩阵 DSH 全版本适配说明：本版本 v0.8.3 已通过源码审计确认与 DSH 至 全部发布版本兼容（、、、、、 CJS factory、cordis.patch.yml
Looking for a dsh-ego-browser alternative? If you're comparing dsh-ego-browser with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
面向 AI Coding Agent 的任务感知工作区上下文检索与生命周期追踪：按当前任务找到、组织并持续追踪最相关的文档、代码与媒体。纯本地、零模型调用、零网络。 Task-aware workspace conte
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
Task-aware reasoning-mode router for DeepSeek Harness: three measured behavior bands (spec/mixed/react) with p
MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and
DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件，覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤，点链接直达仓库。Curated
DeepSeek Harness (dsh) plugin development knowledge base: the 10-chapter development guide, release playbook,
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: