No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by robbyczgw-cla · Codex Skill · ★ 87
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is web-search-plus-plugin safe to install? View the security audit →
web-search-plus-plugin-v2 Native OpenClaw plugin for one clean set of web tools. Current version: 3.1.0 It registers: — Routing v2 intelligent multi-provider web search with research mode and canonical-source reranking — Tavily-first URL extraction across supported providers — in-memory runtime routing preferences manager is removed in v3.0.0. Use search plus extraction; fewer tools, less mush. Install ClawHub: Source: Quick setup You only need one provider configured to start. The recommended starter stack is: You.com for fast snippets / factual queries Serper for Google-style local, shopping, and community search Linkup for source-grounded search and citations Onboarding CLI: Runtime credent
| Stars | 87 |
| Forks | 8 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.8526555838229/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-28 |
| Created | 2026-02-19 |
| Platforms | browser, node |
| Est. Tokens | ~42k |
Explore other popular codex skill tools:
web-search-plus-plugin is OpenClaw plugin: multi-provider web search (Serper/Google, Tavily, Exa) as native agent tool. It is categorized as a Codex Skill with 87 GitHub stars.
web-search-plus-plugin is primarily written in TypeScript.
You can find installation instructions and usage details in the web-search-plus-plugin GitHub repository at github.com/robbyczgw-cla/web-search-plus-plugin. The project has 87 stars and 8 forks, indicating an active community.
web-search-plus-plugin is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: