ClawHub
Back to skill

Security audit

Resume

Security checks across malware telemetry and agentic risk

Overview

This is a resume-writing skill with no executable code or system access; its main risk is that it may draft labeled assumptions the user must verify.

Install only if you are comfortable with the agent drafting a polished resume from incomplete notes. Review and correct every inferred detail marked as assumed, especially employment history, dates, credentials, company names, contact information, and performance metrics, before sending the resume to an employer.

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

Medium
Confidence
90% confidence
Finding
The skill explicitly tells the model to always produce a complete resume by inferring missing details instead of asking clarifying questions. Even though it later says assumptions should be labeled and metrics should not be silently fabricated, this creates pressure to generate plausible but unverifiable personal history, employers, dates, or achievements, which can misrepresent the user and cause downstream fraud, reputational harm, or failed background checks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.