Image To Video Journey

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:44 PM UTC
• Version:
  1.0.0

Overview

This skill is a cloud image-to-video connector with expected external uploads and token use, but users should understand their media and prompts are sent to NemoVideo.

Install only if you are comfortable sending selected photos, videos, audio, prompts, and related session metadata to mega-api-prod.nemovideo.ai for cloud processing. Use your own NEMO_TOKEN when possible, avoid uploading sensitive personal media unless you trust the provider's terms, and monitor credits or account usage.

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 (4)

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The skill instructs the agent to obtain an anonymous token from a third-party service and generate a client identifier when no local credential is present. That expands the skill's behavior from simple media transformation into autonomous account/session provisioning against a remote backend, which can create undeclared data sharing, abuse of free-tier resources, and user activity tracking without explicit consent.

Context-Inappropriate Capability

Low

• Confidence: 82% confidence
• Finding: The skill derives platform/install-path metadata from local filesystem locations to populate headers sent to the backend. While not highly sensitive by itself, this collects local environment information unrelated to the core photo-to-video function and transmits it externally, increasing fingerprinting and reducing user privacy.

Vague Triggers

Medium

• Confidence: 77% confidence
• Finding: The activation examples are broad and overlap with ordinary user requests about photos, videos, exporting, and uploads. Weak activation boundaries can cause the skill to trigger unexpectedly, leading users to send prompts or media to the remote backend without realizing a third-party workflow has been invoked.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill directs the agent to establish a backend connection, create sessions, and process user inputs through a remote API, but it does not clearly warn users that their media and prompts will be transmitted off-device. This creates a meaningful transparency and privacy issue, especially because users may upload personal travel photos and descriptive text.

VirusTotal

62/62 vendors flagged this skill as clean.