ClawHub
Back to skill

Security audit

UGC Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only UGC brief-writing skill with no code execution, persistence, credential access, or hidden agent-control behavior.

Before installing, treat the usage-rights sections as drafting help, not legal advice. Make sure any creator license, paid-ad usage, editing rights, exclusivity, whitelisting, duration, and territory terms are clearly agreed in writing and comply with applicable platform rules and local law.

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
90% confidence
Finding

The skill recommends broad or perpetual content rights as a default and frames full buyouts as standard, but it does not warn users to obtain informed creator consent, ensure contracts clearly define scope, or consider platform, privacy, likeness, and employment/contractor law implications. This can lead users to overclaim usage rights, reuse creator content beyond agreed terms, or create legal disputes over image, voice, editing, and paid advertising usage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.