ClawHub
Back to skill

Security audit

PDF Reader

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local PDF-to-Markdown converter that reads a user-selected PDF and writes a user-selected Markdown file.

Install this only if you are comfortable with a local converter reading the PDFs you point it at and writing Markdown to the output path you choose. For sensitive PDFs, review the generated output path and visually verify OCR-derived numbers before relying on them.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly invokes a local Python script that reads a user-specified PDF and writes a user-specified Markdown file, which gives it shell execution and file-write capability despite no declared permissions. This is not inherently malicious, but the missing permission declaration reduces transparency and can cause downstream agents or users to invoke a skill with stronger capabilities than expected.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger text is broad enough to activate on general requests like reading or extracting PDF content, including use by other workflows, which can cause the skill to run in more situations than strictly necessary. Over-broad activation increases the chance of unintended file processing or automatic execution of a shell-backed converter on sensitive local documents without an explicit user step narrowing scope.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.