Back to skill

Security audit

Pdf Text Extract

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward PDF text extraction skill with disclosed terminal/file output and no evidence of hidden access, persistence, or exfiltration.

Before installing, treat extracted PDF text as potentially sensitive: avoid sending confidential documents to terminal logs or shared output paths, and verify the output filename because it will be overwritten if chosen.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill describes extracting PDF text and optionally writing it to an output file, but it does not warn users that PDFs often contain sensitive or regulated information and that extracted text may be exposed in terminal history, logs, or saved to disk. This omission can lead to accidental disclosure, especially when users process confidential documents in shared or monitored environments.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The module docstring and CLI description emphasize extracting plain text from PDF files, which suggests a conversion/extraction behavior. However, the implementation also performs filesystem write operations when --output is provided, creating a side effect not reflected in the top-level documentation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.