Trusted — Risk Score 0/100
Last scan:2 days ago Rescan
0 /100
html-extract
Extract content from HTML pages and files using MinerU, converting to clean Markdown
The html-extract skill is a well-documented wrapper for the legitimate open-source MinerU tool that converts HTML to Markdown. No malicious behavior detected.
Skill Namehtml-extract
Duration28.5s
Enginepi
Safe to install
This skill is safe to use. Ensure MINERU_TOKEN is stored securely and not logged or exposed.
ResourceDeclaredInferredStatusEvidence
Shell WRITE WRITE ✓ Aligned SKILL.md:15 - Runs mineru-open-api CLI commands
Network READ READ ✓ Aligned SKILL.md:15 - Extracts from remote URLs via mineru-open-api
Filesystem READ,WRITE READ,WRITE ✓ Aligned SKILL.md:13 - Reads local HTML files, writes output to -o directory
Environment READ READ ✓ Aligned SKILL.md:19 - Uses MINERU_TOKEN environment variable
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:45

File Tree

1 files · 3.0 KB · 59 lines
Markdown 1f · 59L
└─ 📝 SKILL.md Markdown 59L · 3.0 KB

Dependencies 1 items

PackageVersionSourceKnown VulnsNotes
mineru-open-api * npm or go No CLI tool installed via npm or go install, versions not pinned in SKILL.md

Security Positives

✓ Well-documented skill with clear purpose and usage
✓ Uses open-source tool (MinerU by OpenDataLab/Shanghai AI Lab)
✓ All shell commands are explicitly documented
✓ Authentication token required but not harvested or exfiltrated
✓ Standard npm/go installation methods used
✓ No base64, eval, or obfuscated code patterns
✓ No sensitive path access (~/.ssh, ~/.aws, etc.)
✓ No data exfiltration or credential theft
✓ Output paths are user-controlled via -o flag