Scan Report
5 /100
html-to-html
Clean and restructure HTML documents using MinerU. Takes messy or complex HTML and produces clean, well-formatted HTML output.
This is a thin wrapper skill around the open-source MinerU CLI tool for HTML cleanup, with all capabilities declared in SKILL.md and no hidden functionality.
Safe to install
No action needed. The skill is safe to use as documented.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | READ | READ | ✓ Aligned | SKILL.md: 'local .html file' / 'extract page.html' |
| Filesystem | WRITE | WRITE | ✓ Aligned | SKILL.md: '-o ./out/' for output directory |
| Network | READ | READ | ✓ Aligned | SKILL.md: 'crawl https://example.com/article' for remote URLs |
| Environment | READ | READ | ✓ Aligned | SKILL.md: 'export MINERU_TOKEN' for API token |
| Shell | WRITE | WRITE | ✓ Aligned | SKILL.md: invokes mineru-open-api CLI via npm/go |
2 findings
Medium External URL 外部 URL
https://mineru.net SKILL.md:4 Medium External URL 外部 URL
https://mineru.net/apiManage/token SKILL.md:42 File Tree
1 files · 3.0 KB · 59 lines Markdown 1f · 59L
└─
SKILL.md
Markdown
Security Positives
✓ All capabilities are explicitly declared in SKILL.md
✓ No scripts or code files included — purely a documentation wrapper
✓ Uses a well-known open-source project (MinerU, OpenDataLab/Shanghai AI Lab)
✓ No credential exfiltration — MINERU_TOKEN is used only for the declared API
✓ No sensitive path access or hidden file operations
✓ No base64, eval, or obfuscated code
✓ No external IP hardcoding or C2 indicators