Image To Video Converter

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.0

Overview

This is a coherent cloud image-to-video skill, but users should understand that media, prompts, and a NemoVideo token/session are sent to an external service.

Install only if you are comfortable sending selected images, audio/video files, prompts, and render metadata to mega-api-prod.nemovideo.ai. Use a dedicated NEMO_TOKEN if possible, avoid confidential media unless you trust the provider's terms, and clarify ambiguous prompts before the agent sends them to the backend.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The skill automatically acquires an anonymous bearer token and creates an authenticated backend session when no user-provided token exists. That expands the skill from simple media conversion into autonomous account/session provisioning against a third-party service, which can cause unintended external access, silent data transmission, and abuse of free-tier credentials without explicit user consent.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: Routing 'everything else' to the SSE generation/edit action is an overly broad trigger that can capture unrelated user requests and send them to the remote backend. In this skill, that means arbitrary text may be transmitted externally and acted on in an authenticated session even when the user did not clearly request video processing.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to obtain anonymous tokens and create backend sessions without a user-facing disclosure that files, prompts, and metadata will be sent to an external service. For an image-upload workflow, this is particularly sensitive because users may provide personal or proprietary media and reasonably expect clear notice before transmission.

VirusTotal

64/64 vendors flagged this skill as clean.