by 安全扫描
OpenClaw
安全
high confidenceThe skill's requirements and runtime instructions align with its stated purpose (running the MinerU CLI to convert PDFs to HTML); nothing requests unrelated credentials or installs arbitrary code from unknown URLs.
评估建议
This skill is essentially documentation for using the MinerU CLI and appears coherent. Before installing: 1) Verify mineru-open-api is the official MinerU package (check the npm page and the GitHub repo linked in SKILL.md). 2) Create a dedicated MinerU token with minimal scope and do not reuse other service credentials. 3) If you install via npm, review the package's install scripts and source code if you require tightened supply-chain control. 4) Prefer running the CLI in a sandbox or CI runner...详细分析 ▾
✓ 用途与能力
The skill is an instruction-only wrapper for the MinerU CLI. Declared requirements (mineru-open-api binary and MINERU_TOKEN) directly match the described functionality (calling mineru-open-api extract to produce HTML). There are no unrelated binaries or extra credential claims.
✓ 指令范围
SKILL.md instructs the agent to run the mineru-open-api CLI (extract, auth) against local files or URLs and to use MINERU_TOKEN. It does not instruct reading other environment variables, unrelated system files, or exfiltrating data to unexpected endpoints.
✓ 安装机制
Install options are npm (mineru-open-api) or go install from a GitHub repo (github.com/opendatalab/...). Both are standard, traceable mechanisms. No downloads from untrusted shorteners or personal IPs are used. (As usual with npm, postinstall scripts are possible; review package sources if you require stricter controls.)
✓ 凭证需求
Only a single token (MINERU_TOKEN) is required and is justified by the CLI's auth flow. No other credentials or config paths are requested. Users should confirm the token's scope and avoid reusing high-privilege tokens.
✓ 持久化与权限
The skill is not always-enabled and does not request persistent modification of other skills or system-wide settings. Autonomous invocation is allowed but this is the platform default and not a reason to flag the skill by itself.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv0.4.02026/4/1
SEO: expand description for better ClawHub vector search discovery
● 无害
安装命令 点击复制
官方npx clawhub@latest install pdf-to-html
镜像加速npx clawhub@latest install pdf-to-html --registry https://cn.clawhub-mirror.com
技能文档
Convert PDF files to HTML using MinerU.
Install
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Quick Start
# Convert PDF to HTML (requires token)
mineru-open-api extract report.pdf -f html -o ./out/# From URL
mineru-open-api extract https://example.com/report.pdf -f html -o ./out/
# With language hint
mineru-open-api extract report.pdf -f html --language en -o ./out/
Authentication
Token required:
mineru-open-api auth # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable
Create token at: https://mineru.net/apiManage/token
Capabilities
- Supported input: .pdf (local file or URL)
- Output format: HTML (
-f html) - HTML output requires
extractwith token — not available inflash-extract - Language hint with
--language(default:ch, useenfor English) - Page range with
--pages(e.g.1-10)
Notes
- HTML output (
-f html) is only available viaextractwith token - Output goes to stdout by default; use
-oto save to a file - All progress/status messages go to stderr; document content goes to stdout
- MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制
免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制