Trusted — Risk Score 0/100
Last scan:2 days ago Rescan
0 /100
html-ocr
OCR for HTML pages containing image-embedded or scanned content using MinerU by OpenDataLab
Documentation-only skill describing a legitimate open-source CLI tool (MinerU) for HTML OCR; no executable code present.
Skill Namehtml-ocr
Duration13.8s
Enginepi
Safe to install
Safe to use as described. The skill contains only SKILL.md documentation—no scripts or code to execute.
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:39

File Tree

1 files · 2.7 KB · 54 lines
Markdown 1f · 54L
└─ 📝 SKILL.md Markdown 54L · 2.7 KB

Security Positives

✓ Skill is documentation-only with no executable code — no attack surface
✓ Tool (MinerU) is open-source and verifiable (github.com/opendatalab/MinerU)
✓ All capabilities clearly declared in SKILL.md: file read, OCR via external CLI, token-based auth
✓ No subprocess, shell, network, or environment access from within the skill
✓ No sensitive file access, no credential harvesting, no exfiltration
✓ Token-based authentication is standard and appropriate for a cloud OCR API