Image To Video Leonardo Ai

• Outcome: Pass
• Latest audit: May 29, 2026, 8:41 PM
• Version:
  1.0.0

Overview

This is a cloud image-to-video skill whose network use and media uploads fit its purpose, but users should be aware that prompts and files are sent to an external Nemo Video backend.

Install only if you are comfortable sending the images, prompts, uploaded media, and related metadata you provide to Nemo Video's cloud service. Avoid confidential or proprietary media unless you trust that provider, and ask the agent to confirm before uploading files, generating, or exporting when your request is ambiguous.

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
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 75% confidence
• Finding: The trigger phrases are very broad and generic, which increases the chance the skill activates on routine user language unrelated to an intentional request for this external service. In this skill's context, unintended activation matters because it can initiate networked processing and token/session creation against a third-party backend without clear user intent.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The routing table contains an 'Everything else' catch-all that sends arbitrary requests into the SSE workflow, making overbroad activation highly likely. Because this skill transmits prompts to an external cloud API and can manipulate session state, an ambiguous catch-all expands the chance of unintended data disclosure or unexpected remote actions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill directs users to share images and prompts but does not clearly warn that those files and instructions are sent to an external cloud service for processing. This is dangerous because users may unknowingly upload sensitive or proprietary media, believing processing is local or agent-internal when it is actually transmitted to a third party.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The instruction to 'keep the technical details out of the chat' suppresses disclosure about authentication, session creation, and third-party network processing. In a skill that uploads user media to an external API, intentionally hiding those facts materially undermines informed consent and increases privacy and data-handling risk.

Natural-Language Policy Violations

Low

• Confidence: 68% confidence
• Finding: Forcing the session language to English without user choice is not a severe security issue, but it can degrade reliability and user comprehension, especially for multilingual users. In safety-sensitive flows, reduced comprehension can indirectly worsen consent and error handling because backend responses may not align with the user's language expectations.

VirusTotal

66/66 vendors flagged this skill as clean.