ClawHub
Back to skill

Security audit

Resume

Security checks for vulnerabilities and agentic risk

Overview

This resume-writing skill has no code or system-access behavior, but it pushes the agent to invent missing resume facts instead of asking the user, which could create misleading professional claims.

Review carefully before installing. If used, treat every assumed item as draft-only, remove or verify inferred employers, dates, titles, education, certifications, contact details, achievements, and metrics before submitting any resume.

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
Findings (1)

other

Warning
Location
SKILL.md:20
Finding

Unsafe Fabrication of Missing Professional Information

Content
View full analysis
Remediation
View remediation

SkillSpector

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly tells the agent to fill in missing resume details with specific, realistic inferences and to avoid asking clarifying questions, while elsewhere warning not to fabricate or inflate numbers. That contradiction can still cause the model to generate false employment history, dates, tools, or outcomes that a user may submit as factual, creating deception, reputational harm, and potential fraud risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.