AI-powered PDF organizer with smart naming

AI tool that categorizes PDFs by topic, extracts metadata, renames files smartly, and organizes them into hierarchical folders automatically.

Security Scan

The skill's instructions match a PDF-organizer purpose but conflict with its registry metadata and omit the actual code — plus it directs sending PDF contents to external APIs and storing API keys in config files, which raises data-exfiltration and provenance concerns.

Purpose & Capability

The SKILL.md describes a PDF organizer that uses OpenAI/Kimi APIs to analyze content and rename/move files — that capability aligns with the name. However the registry metadata declares no required credentials or config paths while the instructions explicitly require an OpenAI or Kimi API key (configured in config.json). This mismatch between declared requirements and the runtime instructions is incoherent.

Instruction Scope

The instructions tell the agent/user to run python pdf_organizer.py and reference multiple project files (modules/, requirements.txt, setup.py) but there are no code files in the package — the skill is instruction-only. The SKILL.md also implies sending extracted PDF text to external APIs (OpenAI/Kimi) but gives no guidance on privacy, truncation, or redaction. It also instructs storing API keys in config.json (plaintext), which is insecure. Overall the runtime steps could expose arbitrary PDF contents to external services and the skill gives broad discretion without safety guidance.

Install Mechanism

There is no install specification (instruction-only), which is lower risk from an installation perspective. However, SKILL.md references installing dependencies (requirements.txt, setup.py) and running a local Python script that does not exist in the package — this is inconsistent and means the skill as-published is incomplete or misleading.

Credentials

Registry metadata lists no required environment variables or primary credential, but the SKILL.md requires an OpenAI or Kimi API key. The skill also suggests storing that key in config.json rather than using a declared/secure environment variable. Requesting an external API key for analyzing user documents is proportionate to the feature, but the omission from the declared requirements and the insecure storage recommendation are problematic.

Persistence & Privilege

The skill does not request persistent/always-on privileges and uses default autonomous invocation behavior. It does not declare modifications to other skills or system-wide settings. No concerns about persistence or elevated platform privileges were found.

What to consider before installing

Before installing or running this skill, ask the publisher for the source code or a repository link (the package currently contains only SKILL.md but claims multiple Python files). Verify where and how the API key is supplied (prefer environment variables or a secrets manager over plaintext config.json). Be aware the skill will send extracted PDF text to external APIs (OpenAI/Kimi) — do not run it on sensitive or confidential documents until you’ve reviewed the code and data handling. If you want to try it safely: request the code, run it from a reviewed repo on an isolated test machine or VM with dummy PDFs, confirm exact network endpoints used, and ensure the skill supports a local/offline mode or a provider with data-use/retention controls. If the author cannot produce source or justification for the missing metadata, treat the package as incomplete and avoid giving it access to real documents or credentials.

PDF Organizer Skill

Description

AI-powered PDF organization tool that automatically categorizes and organizes PDF files by topic using GPT analysis.

Features

• AI-Powered Content Analysis: Uses OpenAI/Kimi API to extract titles, authors, and journal names
• Automatic Topic Classification: Classifies PDFs into 10 standard categories (Technology, Finance, Health, Science, Education, Business, Entertainment, Politics, Sports, Other)
• Smart File Naming: Renames files in Title_Author_Journal.pdf format using only underscores
• Hierarchical Organization: Creates topic-based folders with subtopic subfolders
• Batch Processing: Efficiently processes multiple PDFs at once
• Incremental Mode: Only processes new/modified files
• Error Handling: Gracefully handles corrupted PDFs and API failures
• Detailed Logging: Tracks all operations with comprehensive statistics

Requirements

• Python 3.8+
• OpenAI API key or Kimi API key
• PDF files to organize

Usage

1. Configure API key in config.json
2. Place PDF files in input_pdfs/ folder
3. Run: python pdf_organizer.py
4. Organized files appear in organized_pdfs/ folder

Project Structure

pdf_organizer.py          # Main entry point
modules/
  ├── pdf_reader.py       # PDF text extraction
  ├── content_analyzer.py  # OpenAI/Kimi API integration
  ├── folder_manager.py    # Folder creation and management
  └── file_mover.py        # File operations
config.json              # Configuration file
requirements.txt          # Python dependencies
README.md                # Documentation
setup.py                # Setup/initialization script

Configuration Options

• openai_api_key: Your API key (required)
• input_folder: Folder containing PDFs to organize
• output_folder: Destination folder for organized PDFs
• model: GPT model to use (gpt-3.5-turbo or moonshot-v1-8k)
• api_provider: API provider ("openai" or "kimi")
• dry_run: Preview mode without moving files (true/false)
• incremental: Only process new/modified files (true/false)
• max_chars: Maximum characters to analyze from each PDF
• custom_topics: Custom topic mappings

Example Output

Organized files are named: Title_Author_Journal.pdf Example: Visual_SLAM_What_Are_the_Current_Trends_and_What_to_Expect_Ali_Tourani,_Hriday_Bavle,_Jose_Luis_Sanchez-Lopez,_and_Holger_Voos_Sensors.pdf