Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Lsp Client

v1.0.2

Connects to external Language Server Protocol (LSP) servers via stdio to provide code intelligence like goto definition, find references, hover, and symbol s...

0· 108·0 current·0 all-time
byECsss@olveww-dot

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for olveww-dot/hermes-lsp-client.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Lsp Client" (olveww-dot/hermes-lsp-client) from ClawHub.
Skill page: https://clawhub.ai/olveww-dot/hermes-lsp-client
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install olveww-dot/hermes-lsp-client

ClawHub CLI

Package manager switcher

npx clawhub@latest install hermes-lsp-client
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name/description match the implementation: code shows an LSP server manager that spawns language-server processes and LSP command wrappers. All required capabilities (child processes, stdio JSON-RPC, reading files) are consistent with providing LSP features.
Instruction Scope
SKILL.md instructs installing LSP servers and contains an install one‑liner that downloads from GitHub. Runtime code will read arbitrary file paths (fs.readFile) to open/update files and will spawn local server binaries; this is expected for an LSP client but means the skill can access any file the agent is permitted to open and forward LSP responses back to the agent.
Install Mechanism
No formal install spec in registry, but SKILL.md provides a curl | tar command that downloads a main.tar.gz from a third‑party GitHub repository. Using GitHub releases is common, but downloading and executing archive contents from an external repo is higher risk than a registry-managed install and should be verified.
Credentials
The skill declares no required env vars or credentials (appropriate). Implementation spawns processes with env: { ...process.env, ...config.env }, which is typical but means child LSP servers inherit the agent's entire environment (potentially exposing secrets to local child processes). Also some server commands use 'npx' which may fetch packages at runtime.
Persistence & Privilege
Skill is not always-enabled and doesn't request elevated or persistent platform privileges. Install script copies files into the user skills directory only; it does not modify other skills or system-wide config.
Assessment
This skill is coherent with its stated purpose (a local LSP client) but before installing you should: 1) inspect the repository the SKILL.md install one‑liner points to (olveww-dot/openclaw-hermes-claude) to ensure you trust that source; 2) be aware the skill will spawn local language‑server processes and read any files you ask it to open—avoid passing sensitive file paths (e.g., secrets, SSH keys, system password files) to LSP commands; 3) note child processes inherit your environment, so secrets present in your environment could be visible to language servers; 4) if you allow runtime use of 'npx' or similar, be aware it can download packages from the network at runtime; and 5) if you need higher assurance, run the skill in an isolated environment or review the TypeScript sources (server-manager.ts, lsp-commands.ts) line-by-line before enabling.
src/server-manager.ts:75
Shell command execution detected (child_process).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.

Like a lobster shell, security has layers — review code before you run it.

latestvk97bzpfme05q369xtzm9kg40bh857kcw
108downloads
0stars
3versions
Updated 1w ago
v1.0.2
MIT-0

LSP Client Skill

🛡️ OpenClaw 混合进化方案 — 将 Hermes-agent(100K ⭐)+ Claude Code 核心能力移植到 OpenClaw

Skill Name: lsp-client

Description: Provides code intelligence (goto definition, find references, hover, document symbols) by connecting to external LSP servers via stdio.

Trigger Keywords: 跳转到定义, 查找引用, 悬停提示, 符号搜索, goto definition, find references, hover, document symbol


🚀 一键安装

mkdir -p ~/.openclaw/skills && cd ~/.openclaw/skills && curl -fsSL https://github.com/olveww-dot/openclaw-hermes-claude/archive/main.tar.gz | tar xz && cp -r openclaw-hermes-claude-main/skills/hermes-lsp-client . && rm -rf openclaw-hermes-claude-main && echo "✅ lsp-client 安装成功"

What This Skill Does

This skill acts as an LSP client that communicates with external Language Server Protocol (LSP) servers. LSP is the protocol VSCode uses for code intelligence — this skill gives OpenClaw the same capabilities.

Requirements

You must install LSP servers yourself. This skill is just the client.

Supported LSP Servers

LanguageServerInstall
TypeScript/JavaScripttypescript-language-servernpm i -g typescript-language-server
Pythonpyright or jedi-language-serverpip install pyright
Rustrust-analyzerrustup component add rust-analyzer
Gogoplsgo install golang.org/x/tools/gopls@latest
C/C++clangdInstall via LLVM or your package manager
Vuevolarnpm i -g @vue/language-server

Configuration

Add LSP server configs to your TOOLS.md or skill config:

const LSP_SERVERS = {
  'typescript': {
    command: 'typescript-language-server',
    args: ['--stdio'],
    extensionToLanguage: {
      '.ts': 'typescript',
      '.tsx': 'typescript',
      '.js': 'javascript',
    },
  },
}

Commands

Goto Definition

  • Trigger: "跳转到定义", "goto definition"
  • Args: filePath:line:character
  • Returns: File path and line/column of the definition

Find References

  • Trigger: "查找引用", "find references"
  • Args: filePath:line:character
  • Returns: List of all reference locations

Hover

  • Trigger: "悬停提示", "hover"
  • Args: filePath:line:character
  • Returns: Type information and documentation

Document Symbols

  • Trigger: "符号搜索", "document symbols", "outline"
  • Args: filePath
  • Returns: Tree of symbols (functions, classes, etc.)

Architecture

lsp-commands.ts   — High-level commands (gotoDef, findRefs, etc.)
server-manager.ts  — LSP server lifecycle & routing
protocol.ts        — LSP protocol type definitions

Limitations

  • Requires external LSP servers to be installed
  • Servers communicate via stdio (not sockets)
  • Only supports one server per file extension

🧩 配套技能

本 skill 是 OpenClaw 混合进化方案 的一部分:

Hermesagent(100K ⭐)+ Claude Code 核心能力移植到 OpenClaw

Hermes-agent(100K ⭐)+ Claude Code 核心能力移植到 OpenClaw

🔗 GitHub 项目:olveww-dot/openclaw-hermes-claude

完整技能套件(6个):

  • 🛡️ crash-snapshots — 崩溃防护
  • 🧠 auto-distill — T1 自动记忆蒸馏
  • 🎯 coordinator — 指挥官模式
  • 💡 context-compress — 思维链连续性
  • 🔍 lsp-client — LSP 代码智能(本文)
  • 🔄 auto-reflection — 自动反思

Comments

Loading comments...