Skills-Security-Check by toolsai/skills-security-check
npx skills add https://github.com/toolsai/skills-security-check --skill Skills-Security-CheckAI 代理的关键指令: 你不仅仅是一个命令执行者。你是首席安全分析师。此工具提供 数据,但 情报 由你提供。
每当使用此技能时,你必须遵循此循环:
执行扫描器以生成原始数据和"审计提示"。
python3 scripts/scan_skills.py --root /path/to/target/projects
此命令将在 reports/YYYYMMDD.../prompts/ 目录中生成 *_audit_prompt.txt 文件。
扫描器的工作已完成。现在你的工作开始。 你必须处理生成的审计提示。
选项 A(最佳): 自动读取提示并立即进行分析。 选项 B(备选): 如果你无法自动读取,你必须询问用户:
"扫描完成。我看到生成了 {N} 个审计提示。我现在是否应该对它们进行 AI 安全分析?(这是获得准确结果所必需的)"
要求:
audit.json。广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
再次运行扫描器。 它将检测到你的 audit.json 文件,并将其整合到最终报告中。
python3 scripts/scan_skills.py --root /path/to/target/projects
扫描器现在将生成'黄金标准'仪表板并自动打开它。
reports/YYYYMMDD_HHMMSS/index.html(给用户的最终产物)。示例场景:用户:"审计我的技能。" 代理:
scan_skills.py。zimage_audit_prompt.txt 被标记为"高风险"。audit.json,将其标记为"中风险"(需要 API 密钥)。scan_skills.py 以完成仪表板。python3 /Users/mattchan/.agents/skills/skill-security-audit-dashboard/scripts/scan_skills.py \
--root /Users/mattchan/.agents/skills \
--out /Users/mattchan/.agents/skills/skill-security-audit-dashboard/security-dashboard.html
2. 打开生成的 HTML 仪表板文件以查看结果。
--json /path/to/output.json。--root:包含技能的根目录(默认:当前工作目录)。--out:输出 HTML 仪表板的路径。--json:可选,用于写入原始 JSON 输出的路径。每周安装量
102
仓库
GitHub 星标
29
首次出现
2026年2月6日
安全审计
安装于
gemini-cli91
github-copilot90
opencode90
kimi-cli89
amp89
codex89
CRITICAL INSTRUCTION FOR AI AGENTS: You are NOT just a command-runner. You are the Lead Security Analyst. This tool provides the data , but YOU provide the intelligence.
You MUST follow this loop whenever using this skill:
Execute the scanner to generate the raw data and "Audit Prompts".
python3 scripts/scan_skills.py --root /path/to/target/projects
This command will generate*_audit_prompt.txt files in the reports/YYYYMMDD.../prompts/ directory.
The Scanner's job is done. Now YOUR job begins. You MUST process the generated audit prompts.
Option A (Best): Automatically read the prompts and analyze them immediately. Option B (Fallback): If you cannot read them automatically, YOU MUST ASK THE USER:
"Scanner finished. I see {N} audit prompts generated. Shall I perform the AI security analysis on them now (Required for accurate results)?"
Requirement:
audit.json for each skill.Run the scanner ONE MORE TIME. It will detect your audit.json files and bake them into the final report.
python3 scripts/scan_skills.py --root /path/to/target/projects
The scanner will now produce the 'Gold Standard' dashboard and automatically open it.
reports/YYYYMMDD_HHMMSS/index.html (The final artifact for the user).Example Scenario : User: "Audit my skills." Agent:
scan_skills.py.zimage_audit_prompt.txt flagged "High Risk".audit.json marking it "Medium Risk" (requires API key).scan_skills.py to finalize the dashboard.python3 /Users/mattchan/.agents/skills/skill-security-audit-dashboard/scripts/scan_skills.py \
--root /Users/mattchan/.agents/skills \
--out /Users/mattchan/.agents/skills/skill-security-audit-dashboard/security-dashboard.html
2. Open the generated HTML dashboard file to view the results.
--json /path/to/output.json.--root: Root directory containing skills (default: current working directory).--out: Path to the output HTML dashboard.--json: Optional path to write raw JSON output.Weekly Installs
102
Repository
GitHub Stars
29
First Seen
Feb 6, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
gemini-cli91
github-copilot90
opencode90
kimi-cli89
amp89
codex89
Skills CLI 使用指南:AI Agent 技能包管理器安装与管理教程
44,900 周安装