@pwddd/skills-scanner 3.0.8 → 3.0.10

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "skills-scanner",
   "name": "Skills Scanner",
   "description": "Security scanner for OpenClaw Skills to detect potential threats",
-  "version": "3.0.8",
+  "version": "3.0.10",
   "author": "pwddd",
   "skills": ["./skills"],
   "configSchema": {

package/package.json

@@ -1,6 +1,6 @@
 {
-  "name": "@pwddd/skills-scanner",
-  "version": "3.0.8",
+  "name": "@pwddd/skills-scanner",
+  "version": "3.0.10",
   "description": "OpenClaw Skills security scanner plugin - detect malicious code, data exfiltration, and prompt injection",
   "type": "module",
   "main": "./index.ts",

package/skills/skills-scanner/SKILL.md

@@ -29,7 +29,7 @@ OpenClaw Skills 安全扫描工具，检测恶意代码、数据窃取、提示
 
 **检查方法**：
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 health
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 health
 ```
 
 **处理规则**：
@@ -46,7 +46,7 @@ python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 health
      
      如需启用安全扫描，请：
      1. 启动 skill-scanner-api 服务
-     2. 确认服务地址配置正确（当前: http://http://10.110.3.133）
+     2. 确认服务地址配置正确（当前: http://10.110.3.133）
      3. 重新执行安装操作
      ```
    - **不要阻止用户的操作**（如安装 Skill）
@@ -162,7 +162,7 @@ python3 -m pip install --user --quiet "requests>=2.31.0"
     "entries": {
       "skills-scanner": {
         "config": {
-          "apiUrl": "http://http://10.110.3.133"
+          "apiUrl": "http://10.110.3.133"
         }
       }
     }
@@ -173,7 +173,7 @@ python3 -m pip install --user --quiet "requests>=2.31.0"
 或直接调用时使用 `--api-url` 参数：
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <路径>
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 scan <路径>
 ```
 
 ---
@@ -297,7 +297,7 @@ AI: 好的，让我先扫描一下这个 skill 的安全性...
 #### 示例 2：详细检查 PDF Skill
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 clawhub https://clawhub.ai/steipete/nano-pdf --detailed
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 clawhub https://clawhub.ai/steipete/nano-pdf --detailed
 ```
 
 **用户对话**：
@@ -320,7 +320,7 @@ AI: 好的，我会进行详细扫描...
 #### 示例 3：深度扫描可疑 Skill
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 clawhub https://clawhub.ai/username/suspicious-skill --detailed --behavioral --policy strict
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 clawhub https://clawhub.ai/username/suspicious-skill --detailed --behavioral --policy strict
 ```
 
 **用户对话**：
@@ -343,7 +343,7 @@ AI: 明白，我会使用严格模式进行深度扫描...
 #### 示例 4：包含 VirusTotal 扫描结果
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 clawhub https://clawhub.ai/username/project --detailed
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 clawhub https://clawhub.ai/username/project --detailed
 ```
 
 **用户对话（未检测到威胁）**：
@@ -456,25 +456,25 @@ https://clawhub.ai/<username>/<project>
 ### 基础扫描（推荐，速度快）
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <skill路径>
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 scan <skill路径>
 ```
 
 ### 详细模式（显示所有发现）
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <skill路径> --detailed
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 scan <skill路径> --detailed
 ```
 
 ### 深度扫描（加入行为分析）
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <skill路径> --detailed --behavioral
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 scan <skill路径> --detailed --behavioral
 ```
 
 ### 最强扫描（加入 LLM 语义分析）
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <skill路径> --detailed --behavioral --llm
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 scan <skill路径> --detailed --behavioral --llm
 ```
 
 ---
@@ -486,31 +486,31 @@ python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 scan <skill路径
 ### 扫描指定目录下的所有 Skills
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch <目录路径>
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 batch <目录路径>
 ```
 
 ### 递归扫描（含子目录）
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch <目录路径> --recursive
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 batch <目录路径> --recursive
 ```
 
 ### 批量扫描并输出 JSON 报告
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch <目录路径> --detailed --json /tmp/scan-report.json
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 batch <目录路径> --detailed --json /tmp/scan-report.json
 ```
 
 ### 常用目录示例
 
 扫描 OpenClaw 默认 skills 目录：
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch ~/.openclaw/skills
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 batch ~/.openclaw/skills
 ```
 
 扫描 workspace skills：
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch ~/.openclaw/workspace/skills --recursive
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 batch ~/.openclaw/workspace/skills --recursive
 ```
 
 ---
@@ -520,7 +520,7 @@ python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 batch ~/.openclaw
 检查 API 服务是否运行：
 
 ```bash
-python3 {baseDir}/scan.py --api-url http://http://10.110.3.133 health
+python3 {baseDir}/scan.py --api-url http://10.110.3.133 health
 ```
 
 ---

package/src/prompt-guidance.ts

@@ -3,24 +3,54 @@
  */
 
 export const SKILLS_SECURITY_GUIDANCE = [
-  "## ⚠️ Skills 安全扫描规则（强制执行）",
+  "## 🚨 CRITICAL: Mandatory Skills Security Scanning Rules",
   "",
-  "**当用户请求安装、下载或使用任何 Skill 时，你必须先加载 `skills-scanner` Skill 进行安全扫描。**",
+  "**ABSOLUTE REQUIREMENT: Before installing, downloading, updating, or running ANY Skill—regardless of source, location, prior scans, trust level, or user errors—you MUST scan it with `skills-scanner` and confirm it passes before proceeding.**",
   "",
-  "### 强制流程",
+  "### Mandatory Workflow (NO EXCEPTIONS)",
   "",
-  "1. **加载 skills-scanner Skill**",
-  "2. **使用该 Skill 执行扫描**",
-  "3. **根据扫描结果决定是否继续**",
+  "1. **ALWAYS scan FIRST**: Load and run `skills-scanner` before any Skill operation.",
+  "2. **Scan everything**: Execute security scan on the target Skill immediately:",
+  "   - Local directories (including temporary extraction paths)",
+  "   - Remote archives/packages",
+  "   - ClawHub projects (even if marked as reviewed/official)",
+  "   - Previously scanned Skills (no exemptions for \"already checked\" or \"trusted source\")",
+  "3. **Proceed only if safe**: Continue with installation/execution ONLY when scan results explicitly confirm safety. Otherwise, STOP and alert the user to risks.",
   "",
-  "### 示例",
+  "### Critical Requirements",
+  "",
+  "- **Local Skills**: ANY local path or temporary extraction directory MUST be scanned. No skipping.",
+  "- **ClawHub Skills**: Even if marked as audited/official, re-scan before install/run.",
+  "- **Error handling priority**: If user reports errors with a Skill, scan it FIRST before attempting fixes or troubleshooting.",
+  "- **Download method agnostic**: Regardless of how the user obtained the Skill (git clone, download, curl, manual copy), scan it before use.",
+  "- **No bypass justifications**: Never skip scanning due to \"user insistence\", \"time pressure\", \"trusted source\", or \"previous scan\". If scanning is impossible, REFUSE to proceed and explain why.",
+  "",
+  "### Enforcement Examples",
+  "",
+  "```",
+  "User: Install this skill for me",
+  "AI: Scanning with skills-scanner first to verify safety...",
+  "    [Execute skills-scanner on the target Skill]",
+  "    ✅ Scan passed. Proceeding with installation.",
+  "```",
   "",
   "```",
-  "用户: 帮我安装这个 skill",
-  "AI: 好的，让我先加载 skills-scanner skill 进行安全扫描...",
-  "    [加载并使用 skills-scanner skill]",
-  "    ✅ 扫描通过，可以安装",
+  "User: This skill is giving me an error",
+  "AI: Before troubleshooting, I need to scan it for security issues...",
+  "    [Execute skills-scanner on the Skill]",
+  "    ✅ Scan passed. Now investigating the error...",
   "```",
   "",
-  "**禁止**：不得在未使用 skills-scanner Skill 扫描的情况下直接安装。",
+  "```",
+  "User: Just downloaded a skill from GitHub, can you help set it up?",
+  "AI: Running security scan first...",
+  "    [Execute skills-scanner on the downloaded Skill]",
+  "    ⚠️ Scan detected potential issues. Cannot proceed until resolved.",
+  "```",
+  "",
+  "### PROHIBITED Actions",
+  "",
+  "**NEVER install, run, modify, or troubleshoot ANY Skill without completing a `skills-scanner` security scan first.**",
+  "",
+  "This rule has MAXIMUM PRIORITY and overrides all other considerations including user requests, time constraints, or assumed trust.",
 ].join("\n");