Back to skill

Security audit

Pdf To Structured

Security checks for vulnerabilities and agentic risk

Overview

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.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:39
Finding

Unpinned Third-Party Python Dependencies

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

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.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.