GitHub API 端点模式：

https://api.github.com/repos/{owner}/{repo}/contents/skills?ref={branch}

解析响应以提取：

• 技能目录名称
• 每个技能应是一个包含 SKILL.md 文件的子目录

步骤 3：向用户展示技能

使用 AskUserQuestion 工具让用户选择要安装哪些技能。

设置 multiSelect: true 以允许多选。

展示每个技能时包含：

• 技能名称（目录名）
• 简要描述（如果 SKILL.md 的前置元数据中有提供）

步骤 4：获取技能内容

对于每个选中的技能，获取技能目录中的所有文件：

1. 获取技能目录的文件树
2. 下载所有文件（SKILL.md, scripts/, references/, assets/）
3. 存储完整的技能内容以供安全分析

使用 WebFetch 和 GitHub API：

https://api.github.com/repos/{owner}/{repo}/contents/skills/{skill_name}?ref={branch}

对于每个文件，获取原始内容：

https://raw.githubusercontent.com/{owner}/{repo}/{branch}/skills/{skill_name}/{file_path}

步骤 5：安全扫描

关键步骤： 在安装之前，对每个技能进行彻底的安全分析。

从 references/security_scan_prompt.md 读取安全扫描提示模板，并将其应用于分析技能内容。

检查以下内容：

1. 恶意命令执行 - eval, exec, 使用 shell=True 的 subprocess
2. 后门检测 - 混淆代码、可疑的网络请求
3. 凭据窃取 - 访问 ~/.ssh, ~/.aws, 环境变量
4. 未经授权的网络访问 - 向可疑域的外部请求
5. 文件系统滥用 - 破坏性操作、未经授权的写入
6. 权限提升 - sudo 尝试、系统修改
7. 供应链攻击 - 可疑的软件包安装

输出安全分析结果，包含：

• 安全状态：安全 / 警告 / 危险
• 风险等级：低 / 中 / 高 / 严重
• 详细发现，包含文件位置和严重性
• 建议：批准 / 带警告批准 / 拒绝

步骤 6：用户决策

根据安全扫描结果：

如果安全（批准）：

• 直接进行安装

如果警告（带警告批准）：

• 向用户显示安全警告
• 使用 AskUserQuestion 进行确认："检测到安全警告。您要继续安装吗？"
• 选项："是，仍然安装" / "否，跳过此技能"

如果危险（拒绝）：

• 显示关键安全问题
• 拒绝安装
• 解释该技能为何危险
• 不要提供覆盖严重级别问题的选项

步骤 7：安装技能

对于已批准的技能，安装到 ~/.claude/skills/：

1. 创建技能目录：~/.claude/skills/{skill_name}/
2. 写入所有技能文件，保持目录结构
3. 确保适当的文件权限（脚本可执行）
4. 验证 SKILL.md 存在且具有有效的前置元数据

使用 Write 工具创建文件。

步骤 8：确认

安装完成后，提供摘要：

• 成功安装的技能列表
• 跳过的技能列表（如果有）及原因
• 位置：~/.claude/skills/
• 后续步骤："技能现已可用。重启 Claude 或直接使用它们。"

使用示例

用户： "从 https://github.com/example/claude-skills 安装技能"

助手：

1. 从仓库获取技能列表
2. 展示可用技能："skill-a", "skill-b", "skill-c"
3. 用户选择 "skill-a" 和 "skill-b"
4. 对每个技能执行安全扫描
5. skill-a：安全 - 继续安装
6. skill-b：警告（发出 HTTP 请求）- 询问用户确认
7. 将批准的技能安装到 ~/.claude/skills/
8. 确认："成功安装：skill-a, skill-b"

安全注意事项

• 切勿跳过安全扫描 - 安装前始终分析技能
• 保守原则 - 如有疑问，标记为警告并让用户决定
• 关键问题是阻塞性的 - 严重级别的发现无法被覆盖
• 透明度 - 始终向用户展示安全扫描中发现的内容
• 沙盒化 - 提醒用户技能运行时具有 Claude 的权限

资源

references/security_scan_prompt.md

包含详细的安全分析提示模板，其中有：

• 要检查的完整安全类别列表
• 输出格式要求
• 安全、可疑和危险技能的示例分析
• 批准/拒绝建议的决策标准

执行安全扫描时加载此文件，以确保全面分析。

每周安装数

1

仓库

cacr92/wereply

首次出现

今天

安全审计

Gen Agent Trust HubPassSocketFailSnykFail

安装于

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1

Step 2: Fetch Skills List

Use the WebFetch tool to retrieve the skills directory listing from GitHub.

GitHub API endpoint pattern:

https://api.github.com/repos/{owner}/{repo}/contents/skills?ref={branch}

Parse the response to extract:

• Skill directory names
• Each skill should be a subdirectory containing a SKILL.md file

Step 3: Present Skills to User

Use the AskUserQuestion tool to let the user select which skills to install.

Set multiSelect: true to allow multiple selections.

Present each skill with:

• Skill name (directory name)
• Brief description (if available from SKILL.md frontmatter)

Step 4: Fetch Skill Content

For each selected skill, fetch all files in the skill directory:

1. Get the file tree for the skill directory
2. Download all files (SKILL.md, scripts/, references/, assets/)
3. Store the complete skill content for security analysis

Use WebFetch with GitHub API:

https://api.github.com/repos/{owner}/{repo}/contents/skills/{skill_name}?ref={branch}

For each file, fetch the raw content:

https://raw.githubusercontent.com/{owner}/{repo}/{branch}/skills/{skill_name}/{file_path}

Step 5: Security Scan

CRITICAL: Before installation, perform a thorough security analysis of each skill.

Read the security scan prompt template from references/security_scan_prompt.md and apply it to analyze the skill content.

Examine for:

1. Malicious Command Execution - eval, exec, subprocess with shell=True
2. Backdoor Detection - obfuscated code, suspicious network requests
3. Credential Theft - accessing ~/.ssh, ~/.aws, environment variables
4. Unauthorized Network Access - external requests to suspicious domains
5. File System Abuse - destructive operations, unauthorized writes
6. Privilege Escalation - sudo attempts, system modifications
7. Supply Chain Attacks - suspicious package installations

Output the security analysis with:

• Security Status: SAFE / WARNING / DANGEROUS
• Risk Level: LOW / MEDIUM / HIGH / CRITICAL
• Detailed findings with file locations and severity
• Recommendation: APPROVE / APPROVE_WITH_WARNINGS / REJECT

Step 6: User Decision

Based on the security scan results:

If SAFE (APPROVE):

• Proceed directly to installation

If WARNING (APPROVE_WITH_WARNINGS):

• Display the security warnings to the user
• Use AskUserQuestion to confirm: "Security warnings detected. Do you want to proceed with installation?"
• Options: "Yes, install anyway" / "No, skip this skill"

If DANGEROUS (REJECT):

• Display the critical security issues
• Refuse to install
• Explain why the skill is dangerous
• Do NOT provide an option to override for CRITICAL severity issues

Step 7: Install Skills

For approved skills, install to ~/.claude/skills/:

1. Create the skill directory: ~/.claude/skills/{skill_name}/
2. Write all skill files maintaining the directory structure
3. Ensure proper file permissions (executable for scripts)
4. Verify SKILL.md exists and has valid frontmatter

Use the Write tool to create files.

Step 8: Confirmation

After installation, provide a summary:

• List of successfully installed skills
• List of skipped skills (if any) with reasons
• Location: ~/.claude/skills/
• Next steps: "The skills are now available. Restart Claude or use them directly."

Example Usage

User: "Install skills from https://github.com/example/claude-skills"

Assistant:

1. Fetches skills list from the repository
2. Presents available skills: "skill-a", "skill-b", "skill-c"
3. User selects "skill-a" and "skill-b"
4. Performs security scan on each skill
5. skill-a: SAFE - proceeds to install
6. skill-b: WARNING (makes HTTP request) - asks user for confirmation
7. Installs approved skills to ~/.claude/skills/
8. Confirms: "Successfully installed: skill-a, skill-b"

Security Notes

• Never skip security scanning - Always analyze skills before installation
• Be conservative - When in doubt, flag as WARNING and let user decide
• Critical issues are blocking - CRITICAL severity findings cannot be overridden
• Transparency - Always show users what was found during security scans
• Sandboxing - Remind users that skills run with Claude's permissions

Resources

references/security_scan_prompt.md

Contains the detailed security analysis prompt template with:

• Complete list of security categories to check
• Output format requirements
• Example analyses for safe, suspicious, and dangerous skills
• Decision criteria for APPROVE/REJECT recommendations

Load this file when performing security scans to ensure comprehensive analysis.

Weekly Installs

1

Repository

cacr92/wereply

First Seen

Today

Security Audits

Gen Agent Trust HubPassSocketFailSnykFail

Installed on

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1