Beauty GEO Writer

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.0.1

Overview

This appears to be a prompt-only skill with a language/formatting rigidity issue, not evidence of hidden access or harmful behavior.

Install only if you are comfortable with the skill tending to answer in Chinese and follow strict Chinese-character length rules. Users who need multilingual or accessibility-sensitive output should adjust the skill instructions or avoid relying on it for non-Chinese tasks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The skill hard-codes Chinese-language output behavior and Chinese-character length constraints without stating that this should only apply when the user requests Chinese. In a prompt-only skill, this can override or conflict with user intent, reduce accessibility, and cause the model to ignore system or user language preferences, which is a real prompt-safety and quality-control issue even though it is not directly a code-execution risk.

VirusTotal

64/64 vendors flagged this skill as clean.