by 安全扫描
OpenClaw
安全
high confidenceThe skill does what it says — a small local OCR script to parse receipts into CSV — with no hidden network calls or credential requests, though it omits declaring its runtime dependencies and uses a very simple parsing approach that can misclassify numbers.
评估建议
This skill appears to be what it says: a small local OCR parser that runs pytesseract/Pillow and writes expenses.csv. Before installing or running it: 1) be sure you have the Tesseract binary and Python imaging libs installed (the skill does not declare them as required but SKILL.md expects them); 2) test with sample receipts — the parser uses simple regexes and can misidentify numbers (it may sum non-price numbers), so verify outputs before using for accounting; 3) the script runs locally and d...详细分析 ▾
ℹ 用途与能力
Name, description, SKILL.md, and the included Python script are consistent: the tool runs Tesseract OCR on a supplied image and writes a CSV of detected amounts/items. Minor incoherence: the skill metadata declares no required binaries, but SKILL.md and the script require the Tesseract engine and Python imaging libraries (pytesseract, Pillow). Declaring those dependencies would be expected.
✓ 指令范围
Runtime instructions are narrowly scoped: take a camera photo, run scripts/ocr.py on the image, produce expenses.csv and an MD summary. The script only reads the provided image and writes a local CSV. Concern: the parsing rules and regex in both SKILL.md and code are very simplistic (they match many numeric patterns), so non-monetary numbers may be parsed as amounts and totals will be incorrect.
✓ 安装机制
No install spec is provided (instruction-only install), which minimizes risk. Dependencies are expected to be installed manually (SKILL.md suggests 'pkg install tesseract' and 'pkg install python-pillow'); there are no downloads or obscure install URLs and the included Python code is small and readable.
✓ 凭证需求
The skill requests no environment variables or credentials and the code does not access system credentials, config paths, or network endpoints. This is proportionate for the stated purpose.
✓ 持久化与权限
The skill is user-invocable and not always-enabled. It does not request persistent privileges, does not modify other skills or global agent settings, and runs only when invoked.
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
latestv1.0.02026/3/29
Initial release of receipt-ocr-tracker. - Snap receipts using your device camera and process images with Tesseract OCR. - Automatically parses receipts into CSV expense reports with date, item, amount, and tax. - Supports quick triggers for scanning, OCR, and business receipt tracking. - Outputs freelancer- and small business-friendly CSV/Markdown for Google Sheets. - Includes troubleshooting tips for common setup issues.
● 无害
安装命令 点击复制
官方npx clawhub@latest install receipt-ocr-tracker
镜像加速npx clawhub@latest install receipt-ocr-tracker --registry https://cn.clawhub-mirror.com
技能文档
Quick Start
- Camera snap receipt → save ~/storage/downloads/photo.jpg
- cd scripts
- python3 ocr.py ~/storage/downloads/photo.jpg
- expenses.csv ready.
Examples
Grocery receipt: Input: Milk $5.99, Bread $12.50, Total $19.24 (GST $1.75) Output CSV: date,item,amount,gst,total 2026-03-28,Milk,5.99,0.60,6.59 2026-03-28,Bread,12.50,1.25,13.75 Total,,19.24,1.85,21.09Business lunch: Parses subtotal, tax, tip, total.
Parsing Rules
- Amount: \$(\d+\.\d{2})
- Date: \d{1,2}/\d{1,2}/\d{4}
- Item: Line before amount.
- Total: Last \$ line.
85% accuracy blurry OK.
Usage Workflow
User: "OCR this receipt photo.jpg" Agent: exec ocr.py → CSV attach MD summary.Troubleshooting
No tesseract: pkg install tesseract Blurry: Resnap high light. No PIL: pkg install python-pillow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