可信 — 风险评分 0/100
上次扫描:2 天前 重新扫描
0 /100
nano-banana2
Image generation skill (text-to-image and image-to-image) using the kexiangai.com API
Legitimate image generation skill that calls a documented API endpoint, stores credentials in a user-specified config path, and is fully transparent about all capabilities in SKILL.md.
技能名称nano-banana2
分析耗时23.0s
引擎pi
可以安装
No action needed. The skill is safe to use.
资源类型声明权限推断权限状态证据
网络访问 READ READ ✓ 一致 SKILL.md lines 97-106: curl to https://agent.mathmind.cn/minimalist/api/imgEditN…
文件系统 WRITE WRITE ✓ 一致 SKILL.md lines 62-72: writes to ~/.config/nano-banana2/.env
环境变量 READ READ ✓ 一致 SKILL.md lines 55-60: reads X_API_KEY from environment
命令执行 WRITE WRITE ✓ 一致 scripts/generate.sh: executes curl commands for API calls
1 项发现
🔗
中危 外部 URL 外部 URL
https://agent.mathmind.cn/minimalist/api/imgEditNB2
SKILL.md:100

目录结构

4 文件 · 10.8 KB · 404 行
Markdown 2f · 296L Shell 2f · 108L
├─ 📁 references
│ └─ 📝 api-guide.md Markdown 56L · 949 B
├─ 📁 scripts
│ ├─ 🔧 generate.sh Shell 89L · 1.7 KB
│ └─ 🔧 set_key.sh Shell 19L · 323 B
└─ 📝 SKILL.md Markdown 240L · 7.9 KB

安全亮点

✓ All capabilities explicitly declared in SKILL.md
✓ API endpoint fully documented with request/response structure
✓ Credential storage path clearly specified (~/.config/nano-banana2/.env) with proper chmod 600
✓ No base64/eval/hidden instructions found
✓ No credential exfiltration — API key is used only for the intended API call
✓ No iteration over environment variables for sensitive keys
✓ No remote script execution (curl|bash or wget|sh patterns absent)
✓ Shell scripts are straightforward wrappers around documented curl commands
✓ No sensitive paths accessed beyond the explicitly declared config directory
✓ Input validation and error handling are documented