Twitter

• Outcome: Pass
• Latest audit: May 28, 2026 at 5:44 AM UTC
• Version:
  1.0.1

Overview

This skill appears to be a prompt-only writing assistant for researching and drafting viral tweets, with no evidence of hidden execution, persistence, credential use, or data theft.

Before using it, avoid putting confidential launches, client names, private strategy, personal data, or unreleased product details into prompts that will be searched online. For public or non-sensitive topics, the described behavior is aligned with the skill's purpose.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• 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)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly instructs web research on user-provided niches/topics without warning that prompts, topics, or embedded details may be transmitted to third-party services. If users include confidential campaign plans, client names, unreleased products, or sensitive personal information in the topic, the skill could cause unintended external disclosure and privacy violations.

VirusTotal

64/64 vendors flagged this skill as clean.