可信 — 风险评分 5/100
上次扫描:2 天前 重新扫描
5 /100
nanobanana-pro-prompt-master
NanobananaPro 官方认证首席生图提示词大师,生成 100% 适配 NanobananaPro 平台、可直接复制粘贴落地、零废稿的极致专业生图提示词
This is a pure text-based prompt template skill for AI image generation that only reads knowledge base files and generates structured prompts. No system access, credential harvesting, or malicious behavior detected.
技能名称nanobanana-pro-prompt-master
分析耗时38.6s
引擎pi
可以安装
This skill is safe to use. It operates entirely within the bounds of its declared functionality as a prompt generation tool.

安全发现 1 项

严重性 安全发现 位置
提示
Documentation capability gap
SKILL.md declares filesystem:NONE but the skill functionally needs READ access to load reference knowledge base files. This is a minor documentation alignment issue with no security impact.
All references in SKILL.md reference files but no filesystem permission declared
→ Consider declaring filesystem:READ permission explicitly if the skill framework supports it, for accurate capability mapping.
SKILL.md:1
资源类型声明权限推断权限状态证据
文件系统 NONE READ ✓ 一致 SKILL.md declares NONE but loads references/style-library.md, references/negativ…
网络访问 NONE NONE No network requests observed
命令执行 NONE NONE No shell execution, no subprocess calls
环境变量 NONE NONE No environment variable access
技能调用 NONE NONE No cross-skill invocation
剪贴板 NONE NONE No clipboard access
浏览器 NONE NONE No browser automation
数据库 NONE NONE No database access
8 项发现
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/version-1.0.0-blue.svg
README.md:5
🔗
中危 外部 URL 外部 URL
https://clawhub.ai/skills/nanobanana-pro
README.md:5
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/license-MIT-green.svg
README.md:6
🔗
中危 外部 URL 外部 URL
https://nbpro.org
README.md:231
🔗
中危 外部 URL 外部 URL
https://docs.openclaw.ai
README.md:232
🔗
中危 外部 URL 外部 URL
https://nbpro.org/prompts
references/platform-specs.md:450
🔗
中危 外部 URL 外部 URL
https://docs.nbpro.org
references/platform-specs.md:451
🔗
中危 外部 URL 外部 URL
https://community.nbpro.org
references/platform-specs.md:452

目录结构

10 文件 · 97.5 KB · 3264 行
Markdown 8f · 3190L JSON 2f · 74L
├─ 📁 references
│ ├─ 📝 camera-movement-guide.md Markdown 567L · 12.7 KB
│ ├─ 📝 negative-prompts.md Markdown 311L · 10.6 KB
│ ├─ 📝 platform-specs.md Markdown 456L · 9.0 KB
│ ├─ 📝 prompt-templates.md Markdown 469L · 20.2 KB
│ ├─ 📝 storyboard-template.md Markdown 292L · 13.3 KB
│ └─ 📝 style-library.md Markdown 557L · 15.3 KB
├─ 📋 package.json JSON 19L · 408 B
├─ 📝 README.md Markdown 236L · 5.4 KB
├─ 📋 skill.json JSON 55L · 1.3 KB
└─ 📝 SKILL.md Markdown 302L · 9.4 KB

安全亮点

✓ Pure text/template generation with no executable code
✓ No shell execution, subprocess calls, or system commands
✓ No credential harvesting or sensitive path access
✓ All behavior is transparent and declared in SKILL.md
✓ No network requests or data exfiltration
✓ No base64 encoding, eval, or suspicious patterns
✓ Knowledge bases are static markdown files with no hidden functionality
✓ No .env file or credential storage present
✓ Clean dependency manifest with no vulnerabilities