ClawHub
Back to skill

Security audit

PDF PPTX Watermark

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: locally converts presentations or PDFs into watermarked PDFs, with some ordinary document-processing risk and a few documentation caveats.

Install only if you need local PPT/PDF watermarking. Use it on files you intentionally choose, keep LibreOffice updated, avoid processing untrusted presentations outside a sandbox, and be aware that the advertised phone/QR tuning is not clearly documented in the packaged files.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The README makes a strong safety claim ('Local & safe — no network') while also describing live phone-based tuning via QR code, which strongly implies a local web server, hotspot, or LAN-accessible interface. Misrepresenting network exposure can cause users to run the tool in sensitive environments without appropriate access controls, increasing the chance of unintended remote access or information disclosure.

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The tool sends user-supplied PPT/PPTX files to LibreOffice for conversion, which means untrusted complex document formats are parsed by a large external office suite. If an attacker supplies a crafted document exploiting a LibreOffice parsing vulnerability, this could lead to code execution or compromise of the host running the skill.

Vague Triggers

Medium
Confidence
78% confidence
Finding
Overly broad triggers such as generic phrases like 'convert to PDF' or 'add watermark' can cause the skill to activate for user requests outside its intended document-processing scope. In an agent ecosystem, this may lead to unintended invocation on unrelated files or workflows, increasing the chance of surprising file access or shell-based processing without clear user intent.

Static analysis

No suspicious patterns detected.