Scan Report
0 /100
prompt-refiner
将模糊的用户请求转化为基于四要素框架的详细、可操作提示
This is a pure documentation/methodology skill containing only a SKILL.md guide and evals.json test cases with no executable code, scripts, or potentially dangerous functionality.
Safe to install
This skill is safe to use. No security concerns identified.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | READ | ✓ Aligned | SKILL.md only contains documentation, no file operations required |
| Network | NONE | NONE | — | No network requests in documentation |
| Shell | NONE | NONE | — | No shell commands or subprocess usage |
| Environment | NONE | NONE | — | No environment variable access |
| Skill Invoke | NONE | NONE | — | No skill invocation patterns |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | No browser interaction |
| Database | NONE | NONE | — | No database access |
File Tree
2 files · 12.2 KB · 265 lines Markdown 1f · 222L
JSON 1f · 43L
├─
▾
evals
│ └─
evals.json
JSON
└─
SKILL.md
Markdown
Security Positives
✓ No executable code present - purely documentation
✓ No network requests or external communications
✓ No shell execution, subprocess, or system commands
✓ No credential or sensitive file access
✓ No obfuscation techniques (base64, eval, etc.)
✓ No downloads or remote script execution
✓ Complete documentation transparency - all behavior is declared
✓ Skill is a legitimate prompt engineering methodology
✓ No supply chain risks - no dependencies