ClawHub
Back to skill

Security audit

Korean Resume Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Korean resume and cover-letter template helper that requests resume-relevant personal details but does not add code, tools, persistence, or hidden behavior.

Reasonable to install for drafting Korean resumes, but provide only the personal details needed for the draft and consider using placeholders for phone, email, school, or employer details until the final version is ready.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly collects sensitive personal data such as full name, phone number, email, education, and employment history, but provides no notice about data minimization, storage, retention, redaction, or safe handling. In an agent context, this can lead users to disclose personally identifiable information that may be unnecessarily exposed in prompts, logs, downstream tools, or generated documents.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.