ClawHub

Frontend Cv

Security checks across malware telemetry and agentic risk

Overview

This resume-building skill is coherent for its purpose, but it handles sensitive resume data and may open local previews or load external fonts.

Install only if you are comfortable processing your resume locally with Python scripts. Use a private folder, review generated YAML and HTML before sharing, avoid committing the outputs, consider removing external font links for offline/privacy-sensitive use, and confirm before deleting preview files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read local files, write extracted and rendered resume artifacts, open browser previews, and reference external web fonts, but it declares no permissions or trust boundaries. That creates an authorization gap where users and hosts may not realize the skill can access and persist sensitive resume data or trigger network fetches during rendering/viewing.

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The renderer inserts stylesheet URLs from theme data directly into generated HTML via <link rel="stylesheet"> tags. Although the URL string is HTML-escaped, that does not prevent loading attacker-controlled remote resources, which can leak viewer IP/user-agent, enable tracking, and in some HTML-to-PDF/browser rendering contexts introduce active content or unsafe network access when untrusted themes are allowed.

Missing User Warnings

Low
Confidence
86% confidence
Finding
Automatically opening generated resume previews can expose highly sensitive personal data on screen, in browser history, recent files, synced tabs, or to shoulder-surfing without the user's informed consent. In this skill context, resumes commonly contain names, contact details, employment history, and sometimes addresses, so silent display of previews increases privacy risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The cleanup step instructs deletion of generated preview files without explicit warning or confirmation, which can remove user data or artifacts they may want to inspect, retain, or archive. Because resumes are user-supplied sensitive documents and previews may represent work product, silent deletion can cause data loss and undermine user control over personal information handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal