Back to skill

Security audit

pdf-tool

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward PDF utility skill with ordinary document-processing risks, not evidence of malicious behavior.

Install if you need PDF extraction or editing help, but treat PDFs and extracted text as sensitive. Use new output filenames, keep backups for important documents, and avoid sending extracted confidential content to logs or external services unless you explicitly intend to.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The documentation describes merge, split, and watermark operations that create or modify output artifacts but does not warn users about overwrite risk, file replacement behavior, or unintended alteration of documents. In a file-processing skill, this omission can lead users to choose unsafe output paths or assume operations are non-destructive, causing accidental data loss or corruption.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises text extraction from PDFs without any privacy warning that extracted text may include confidential contract terms, personal data, or other sensitive content. This is risky because users may send extracted text to logs, downstream tools, or chat contexts without realizing they are exposing the full document contents.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal