Image To Video Online Ai

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

This skill appears to provide the advertised cloud image-to-video workflow, but it can automatically connect to a third-party backend and send media or prompts there with broad activation rules and limited upfront disclosure.

Install only if you intend to use NemoVideo's cloud service. Treat uploaded images, prompts, media URLs, and generated project state as data sent to a third party; avoid confidential or sensitive content unless you have reviewed the provider's terms and data handling. Use a dedicated NEMO_TOKEN where possible and supervise uploads, exports, and credit-consuming actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The manifest presents a narrowly scoped JPG-photo-to-video tool, but the body of the skill expands into a broader media editing and file-processing interface with many formats, timeline edits, audio, text overlays, and export behaviors. This scope mismatch can cause users or host systems to grant trust, permissions, or activation based on an understated capability set, increasing the chance of unintended data handling and misuse.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The onboarding language and trigger phrases are broad enough that common words like 'export', 'upload', or vague creative requests may activate the skill unintentionally. In a skill that immediately connects to a remote backend and may acquire anonymous tokens, accidental activation can result in unanticipated network requests and transmission of user content.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill causes user images and prompts to be sent to a third-party remote backend, but the user-facing description does not clearly warn about that data transfer before use. Because the skill handles potentially sensitive media, the lack of explicit disclosure undermines informed consent and can expose personal or proprietary content to external processing unexpectedly.

VirusTotal

66/66 vendors flagged this skill as clean.