ClawHub
Back to skill

Security audit

Doc Parse Tool Free

Security checks across malware telemetry and agentic risk

Overview

This document-parsing skill is not clearly malicious, but it asks for broad execution/write/network-style capabilities without enough scoping or user control.

Review this skill before installing. Use it only with non-sensitive documents unless you understand whether files may be sent to a cloud OCR provider or callback URL, and require explicit confirmation before allowing command execution, writes, exports, or callbacks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
87% confidence
Finding
The skill is presented as a document parsing/OCR tool, but the documentation expands its scope to generic create/query/export/modify/delete operations. That mismatch can mislead users and host agents into granting or invoking broader capabilities than necessary, increasing the chance of unintended file/system actions beyond document parsing.

Description-Behavior Mismatch

Medium
Confidence
82% confidence
Finding
The skill is marketed as a free personal-use parser, yet it requires external API keys and may rely on cloud OCR services. This creates a trust and data-handling mismatch: users may unknowingly send documents to third-party services or incur costs despite the 'free' framing.

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
Callback URL support adds outbound network behavior that is not necessary for basic local document parsing. If not tightly controlled, it can be abused for data exfiltration, SSRF-like access to internal endpoints, or sending processing results to attacker-controlled infrastructure.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The skill declares write and exec capabilities without clearly warning users about filesystem changes, command execution, or how document data may be processed. In an agent context, poor disclosure increases the risk of unsafe use, especially when handling sensitive local files or executing commands derived from user-controlled inputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.