可信 — 风险评分 5/100
上次扫描:22 小时前 重新扫描
5 /100
ai-image-generator
AI图片与视频异步生成技能,调用AI Artist API根据文本提示词生成图片或视频
Legitimate AI image/video generation skill that safely wraps an external API with no malicious behavior detected.
技能名称ai-image-generator
分析耗时30.1s
引擎pi
可以安装
This skill is safe to use. No security concerns identified.
资源类型声明权限推断权限状态证据
文件系统 READ READ ✓ 一致 Only reads user-provided files for upload and writes generated images to specifi…
网络访问 READ READ ✓ 一致 All network requests are to documented API endpoints (staging.kocgo.vip)
命令执行 NONE NONE No subprocess, os.system, or shell execution found
环境变量 READ READ ✓ 一致 Reads AI_ARTIST_TOKEN and FEISHU_WEBHOOK_URL for legitimate API authentication
8 项发现
🔗
中危 外部 URL 外部 URL
https://staging.kocgo.vip/index
README.md:9
🔗
中危 外部 URL 外部 URL
https://staging.kocgo.vip/stage-api/system/fileUpload/upload
SKILL.md:64
🔗
中危 外部 URL 外部 URL
https://kocgo-ai-sales-test.oss-cn-hangzhou.aliyuncs.com/material/100/xxx.png
SKILL.md:75
🔗
中危 外部 URL 外部 URL
https://open.feishu.cn/open-apis/bot/v2/hook/xxx
SKILL.md:515
🔗
中危 外部 URL 外部 URL
https://staging.kocgo.vip/stage-api/ai/AiArtistRecord
references/api.md:103
🔗
中危 外部 URL 外部 URL
https://staging.kocgo.vip/stage-api/ai/AiArtistImage/getInfoByArtistId/
references/api.md:123
🔗
中危 外部 URL 外部 URL
https://your-cdn.com/image.png
references/feishu-integration.md:84
🔗
中危 外部 URL 外部 URL
https://staging.kocgo.vip/stage-api/ai
scripts/generate_image.py:25

目录结构

7 文件 · 62.6 KB · 1959 行
Python 1f · 1008L Markdown 5f · 946L JSON 1f · 5L
├─ 📁 references
│ ├─ 📝 api.md Markdown 125L · 3.0 KB
│ ├─ 📝 chat-integration.md Markdown 69L · 1.8 KB
│ └─ 📝 feishu-integration.md Markdown 159L · 4.2 KB
├─ 📁 scripts
│ └─ 🐍 generate_image.py Python 1008L · 36.3 KB
├─ 📋 _meta.json JSON 5L · 148 B
├─ 📝 README.md Markdown 72L · 1.5 KB
└─ 📝 SKILL.md Markdown 521L · 15.7 KB

依赖分析 1 项

包名版本来源已知漏洞备注
requests * pip No version pinning but requests is a widely-used stable library

安全亮点

✓ Clean, readable Python code with no obfuscation
✓ Comprehensive documentation matches implementation
✓ No shell execution or command injection vulnerabilities
✓ API key only used locally for authentication to the external service
✓ File operations limited to user-specified paths for reference image upload and output
✓ All network requests go to clearly documented API endpoints
✓ No credential harvesting beyond the user's own API key
✓ No sensitive path access (no ~/.ssh, ~/.aws, or .env file reading)
✓ Optional Feishu webhook notification is clearly documented and user-controlled