T08 · Insecure Dependencies
- Location
SKILL.md:39- Finding
Unpinned Third-Party Python Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward PDF data-extraction helper, with ordinary local file output and dependency-installation risks users should manage.
Before installing, use a virtual environment, consider pinning or reviewing dependency versions, and keep extracted spreadsheets or text files in approved secure locations. For confidential PDFs, prefer local Tesseract OCR and require explicit user approval before using any cloud OCR service.
SKILL.md:39Unpinned Third-Party Python Dependencies
The skill repeatedly demonstrates writing extracted PDF contents to local Excel, CSV, JSON, and text files without any warning that construction PDFs may contain sensitive commercial, operational, or personal data. In batch mode, this can amplify exposure by creating many plaintext or spreadsheet artifacts that may be stored in insecure locations, synced automatically, or shared unintentionally.
The manifest describes this skill as extracting structured data from PDFs and converting outputs to Excel/CSV/JSON using OCR and pdfplumber. The quick reference at L440 adds 'Merge PDFs | pypdf | writer.add_page(page)', which is a document manipulation capability unrelated to structured data extraction or format conversion.
No suspicious patterns detected.