Ai 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 know their media and prompts are sent to Nemovideo for processing.

Install only if you are comfortable sending selected images, URLs, prompts, and editing instructions to Nemovideo's cloud service. Avoid confidential or sensitive media unless you trust that provider's privacy and retention practices; use your own NEMO_TOKEN if you want account control.

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 (4)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill is presented as a simple image-to-video converter, but the instructions expose a much broader remote multimedia editing pipeline including audio, text, timeline state, uploads by URL, and multi-format export. This creates a capability mismatch that can mislead users and hosts about what data and actions the skill can perform, increasing the risk of overbroad data handling and unintended external operations.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The catch-all rule routes essentially any prompt not matching a few narrow keywords into the SSE backend, which can cause unrelated user requests to be sent to an external service. This can result in prompt hijacking at the skill-selection layer, unnecessary data disclosure, and unintended invocation of remote actions outside the user's expectation.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill description emphasizes convenience but does not clearly warn that user media, prompts, and editing instructions are transmitted to a third-party cloud rendering service. This undermines informed consent and can expose sensitive images or prompt content to external processing without adequate disclosure.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The automatic setup instructs the agent to authenticate and create sessions against external services on first interaction, including obtaining an anonymous token, without requiring prior user awareness or consent. Silent credential acquisition and outbound network activity on initial use are especially risky because they expand trust boundaries before the user has approved external processing.

VirusTotal

66/66 vendors flagged this skill as clean.