Google Ai Video Generator Free

• Outcome: Review
• Latest audit: May 29, 2026 at 9:32 PM UTC
• Version:
  1.0.0

Overview

This skill is for cloud AI video generation, but it can automatically create a remote session and route broad or ambiguous user requests to a third-party backend.

Install only if you intend to use NemoVideo cloud processing and are comfortable with prompts, uploaded images, videos, and session data being sent to that service. Avoid private or client-owned media unless you have checked the service terms, and explicitly confirm before letting the skill create sessions, upload files, or start generation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (3)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill invites activation with very generic language like sharing text or images and 'I'll get started,' which can match ordinary user conversation rather than an explicit invocation. In an agent environment, this increases the chance the skill activates unintentionally and begins network-backed actions such as token acquisition, session creation, or uploads without a clearly delimited user intent to use this specific integration.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger phrase 'generate my text or images' is overly broad and resembles common natural-language requests users might make in many contexts. Because this skill can automatically authenticate anonymously and contact a remote backend, vague triggers materially raise the risk of accidental activation and unintended data transfer.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The catch-all rule routes 'Everything else' to the SSE action, making the activation boundary highly ambiguous and effectively treating most unmatched prompts as commands for the remote service. In this skill's context, that is more dangerous than a normal ambiguity issue because SSE can transmit arbitrary user text to an external API and drive edits or other backend actions, increasing the chance of unintended remote processing or disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.