ClawHub
Back to skill

Security audit

UGC Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill for drafting UGC creator briefs, with no executable behavior, credentials, persistence, or hidden data access.

Before using generated briefs in live ads, verify that all objective product, health, safety, efficacy, comparative, testimonial, and pricing claims are truthful, substantiated, platform-compliant, and approved for your brand or jurisdiction. Also make sure usage-rights language is reviewed as appropriate for creator contracts.

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
Confidence
93% confidence
Finding
The skill includes example ad-brief language for skincare and product performance claims such as visible skin improvement timelines, fading acne scars, and heat-safety assertions, but it does not instruct users to obtain legal/compliance review or substantiate claims before using them in advertising. In a marketing-brief skill, this omission is materially risky because users may operationalize the examples directly, leading to deceptive, unsubstantiated, or regulated advertising claims.

Static analysis

No suspicious patterns detected.