ClawHub
Back to skill

Security audit

Resume Styles Kit（简历风格生成）

Security checks across malware telemetry and agentic risk

Overview

This is a resume-formatting skill whose file and PDF generation behavior matches its stated purpose, with a privacy wording conflict users should clarify before using real personal data.

Before installing or using this skill, decide whether you want real resume data or placeholder/demo data and make that explicit. If using real personal information, keep outputs local unless you intentionally choose an external service, and review generated HTML/PDF files before sharing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

High
Confidence
97% confidence
Finding
The skill gives conflicting instructions: it first mandates de-identification and forbids real personal data, then later instructs the agent to use the candidate's real information and real project data. In a resume-generation context, this contradiction can cause accidental collection, retention, or inclusion of sensitive personal data in generated artifacts or processing pipelines, increasing privacy and compliance risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.