sampx/skill-security-scanner
skills/backup/skill-security-scanner/SKILL.md
Security scanner for AI agent skills. Scans skills or directories for malicious code including C2 infrastructure, reverse shells, credential exfiltration, malware markers, dynamic code execution, and JS obfuscation. Default JSON output for AI agents. Use after downloading any new skill.
$ install --global
skillsauthnpx skillsauth add sampx/agent-tools skill-security-scannerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 7:13 AM5.1s18 files scanned
SKILL.md
- name:
- skill-security-scanner
- description:
- Security scanner for AI agent skills. Scans skills or directories for malicious code including C2 infrastructure, reverse shells, credential exfiltration, malware markers, dynamic code execution, and JS obfuscation. Default JSON output for AI agents. Use after downloading any new skill.
Skill Security Scanner
对 AI Agent 技能进行静态安全分析，检测 20 种恶意代码模式。默认输出 JSON（节省 token）。
用法
# 扫描单个技能（默认 JSON 输出）
./scripts/scan.sh <skill-directory>
# 详细模式（人类可读日志）
./scripts/scan.sh <skill-directory> --verbose
# 递归扫描目录
./scripts/scan.sh ~/.claude/skills
检测项 (20 项)
| # | 检查项 | 风险等级 | 说明 | |---|--------|----------|------| | 1 | c2_infrastructure | 严重 | 已知 C2 IP 地址 | | 2 | malware_markers | 严重 | AMOS/Stealer 恶意软件特征 | | 3 | reverse_shell | 严重 | 反向 Shell 模式 | | 4 | exfil_endpoints | 严重 | 数据外泄端点 | | 5 | crypto_wallet | 警告 | 加密钱包相关模式 | | 6 | curl_pipe | 警告 | Curl-Pipe 攻击模式 | | 7 | skillmd_injection | 警告 | SKILL.md 可疑安装指令 | | 8 | memory_poison | 严重 | 尝试修改内存文件 | | 9 | env_leakage | 警告 | 访问敏感文件 | | 10 | plaintext_creds | 警告 | 硬编码 API 密钥 | | 11 | base64_obfuscation | 警告 | Base64 混淆模式 | | 12 | binary_download | 警告 | 外部二进制下载 | | 13 | malicious_patterns | 严重 | 已知恶意技能模式 | | 14 | persistence | 警告 | 持久化机制 | | 15 | file_hashes | 严重 | 已知恶意文件哈希 | | 16 | vscode_trojan | 严重 | 可疑 VS Code 扩展 | | 17 | mcp_security | 严重 | MCP 配置提示注入 | | 18 | dynamic_code_execution | 警告 | 动态代码执行 | | 19 | js_obfuscation | 警告 | JavaScript 混淆 | | 20 | url_shorteners | 警告 | 短链接服务 |
退出码
0- 安全 (Risk Score: 0)1- 警告 (Risk Score: 1-99)2- 严重 (Risk Score: 100)
JSON 输出示例
{
"scan_time": "2026-02-25T10:00:00Z",
"target_dir": "/path/to/skill",
"scanner_version": "2.1.0",
"risk_score": 0,
"summary": { "critical": 0, "warning": 0, "safe": 20, "total": 20 },
"status": "safe",
"exit_code": 0,
"checks": [...]
}
IOC 数据库更新
./scripts/update-ioc.sh # 立即更新
./scripts/update-ioc.sh --check # 检查更新
设置自动更新
# 默认每日 02:30 更新
./scripts/setup-auto-update.sh
# 自定义时间 (HH:MM)
./scripts/setup-auto-update.sh --time 03:30
# 或分别指定小时和分钟
./scripts/setup-auto-update.sh --hour 2 --minute 30
# 查看当前定时任务
./scripts/setup-auto-update.sh --list
# 卸载定时任务
./scripts/setup-auto-update.sh --uninstall
威胁签名数据库位于 ioc/ 目录，从上游仓库 adibirzu/openclaw-security-monitor 同步。
Related Skills
sampx/agent-browser
tools
VerifiedTrustedCommunity
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
3SKILL.mdUpdated Jul 29, 2026
sampx/space-master
testing
VerifiedTrustedCommunity
Master specification for WopalSpace. [MUST LOAD FIRST] — Load this skill when Wopal is uncertain how to proceed, task intent is ambiguous, or performing ontology/space maintenance. Triggers: Ambiguous task intent, "what workflow to use", "what skill to load", skill management (install/remove/search), space maintenance (worktrees, sync, PR contribution, promote), multi-space management. [CRITICAL] MUST LOAD whenever interacting with ontology repo operations (update/sync/contribute/promote/PR), even if the user does not explicitly say "upstream sync".
3SKILL.mdUpdated May 11, 2026
sampx/git-worktrees
development
VerifiedTrustedCommunity
Workspace-level Git worktree management — create, list, remove, and prune isolated development environments. Use this skill whenever the user needs to create a worktree, set up an isolated workspace, work on multiple features in parallel, list existing worktrees, check what worktrees exist, remove or delete a worktree, clean up stale worktrees, or manage git working trees in any way. Triggers include "create worktree", "new worktree", "list worktrees", "show worktrees", "remove worktree", "delete worktree", "clean up worktree", "prune worktree", "isolated environment", "parallel development", "worktree for <project>", or any request involving git worktree operations.
3SKILL.mdUpdated Apr 30, 2026
sampx/dev-flow
development
VerifiedTrustedCommunity
Issue/Plan-driven development workflow. Tasks must be backed by a GitHub Issue or Plan. Trigger: issue references like #14, creating issues, creating plans, implementing plans, executing plans, checking plans, verifying plans, Plan lifecycle transitions (approve/complete/verify/archive), decomposing PRDs into Issues. Skip: spec-driven workflows, research/discussion/explanation only, small ad-hoc changes that don't need an Issue or Plan.
3SKILL.mdUpdated Apr 30, 2026