Video Script Gen

• Outcome: Review
• Latest audit: Jun 3, 2026, 12:33 AM
• Version:
  2.1.0

Overview

This markdown-only video script skill does not run code, but it mixes normal use with off-platform PayPal, Telegram, and crypto payment solicitation.

Read the skill carefully before installing. It appears low risk for your device because it is only markdown, but do not treat the PayPal, Telegram, or USDT payment path as platform-vetted, and avoid using it to create unsubstantiated health or weight-loss advertising claims.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The file content is primarily a commercial landing page that solicits payment and redirects users to external purchase channels instead of providing the declared operational skill behavior. This is dangerous because it abuses the skill mechanism as an advertising and monetization vehicle, misleading users and potentially steering them to unvetted off-platform transactions.

Context-Inappropriate Capability

Medium

• Confidence: 99% confidence
• Finding: The skill explicitly solicits PayPal and crypto payments and promotes external sales channels unrelated to the safe operation of a script-writing skill. This creates phishing/fraud and trust-boundary risks by encouraging users to transact outside the platform with no security assurances or necessity for the stated functionality.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The invocation guidance is loosely framed and mixes normal usage with sales messaging, without clear boundaries on when the skill should activate or what requests it should refuse. In context, this increases the chance of inappropriate triggering for promotional or potentially harmful marketing content, including questionable product promotions.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The examples include generating promotional content for a weight loss supplement, but there are no warnings or guardrails around regulated or potentially deceptive marketing claims. This is dangerous because it may normalize creation of unsafe health-related ads without disclosures, substantiation requirements, or policy restrictions.

VirusTotal

62/62 vendors flagged this skill as clean.