美光车险PDF转Excel
v2.0.0Automatically extracts 14 fields from car insurance PDF policies of 5 companies and outputs the data into an Excel file.
⭐ 0· 18·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The script implements PDF-to-Excel extraction for the stated insurance fields and companies, so the requested capabilities align with the name/description. Minor mismatch: SKILL.md lists dependencies (pymupdf) that do not match the code (which imports pdfplumber). Also the script hardcodes Windows Desktop paths (C:\Users\Administrator\Desktop\...), which is functional but inflexible.
Instruction Scope
Runtime instructions are narrow and consistent: run python scripts/run_extract.py, input and output paths are explicit. The script only reads local PDF files from the hardcoded folder and writes an Excel file. No external network endpoints, no environment variables, and no access to unrelated files are present. Concern: hardcoded Administrator Desktop path makes it Windows-specific and may cause accidental processing of files if run under that user; the script is not parameterized.
Install Mechanism
No install spec (instruction-only skill) and the included script has no downloader/installer — lowest install risk. User must install Python and Python packages manually. Note the SKILL.md lists pandas, openpyxl, pymupdf, but the code imports pandas, openpyxl (via to_excel) and pdfplumber — ensure pdfplumber is installed instead of/alongside pymupdf.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The script accesses only local PDF files in the specified folder; it processes PII contained in insurance policies but does not exfiltrate it or request secrets.
Persistence & Privilege
always:false and normal invocation settings. The skill does not attempt to persist configuration or modify other skills or system settings.
Assessment
This skill appears to do what it says: extract 14 fields from car-insurance PDFs into an Excel file and contains no network or credential usage. Before running: 1) Fix the dependency mismatch — install pdfplumber (and pandas, openpyxl) even though SKILL.md lists pymupdf. 2) Review or change the hardcoded PDF_FOLDER and OUTPUT_FILE to point to a safe, intended directory (or modify the script to accept command-line args) to avoid unintentionally processing files from C:\Users\Administrator\Desktop. 3) Note it processes sensitive personal data (names, ID numbers, phone, VIN, license plates); run it in a trusted environment and on ethically/legally allowed data. 4) Because the source is 'unknown', consider reviewing the code locally (you already have it) or running it in an isolated VM/container if you are uncomfortable. If you want broader OS support or safer operation, request the author to parameterize input/output paths and correct the dependency list.Like a lobster shell, security has layers — review code before you run it.
car-insurancevk9740p82wyh15qj6wwsg4r9ny58511dnexcelvk9740p82wyh15qj6wwsg4r9ny58511dninsurancevk9740p82wyh15qj6wwsg4r9ny58511dnlatestvk9740p82wyh15qj6wwsg4r9ny58511dnpdfvk9740p82wyh15qj6wwsg4r9ny58511dn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.