Ai Video Editor Mobile App

• Outcome: Review
• Latest audit: May 28, 2026 at 8:55 AM UTC
• Version:
  1.0.0

Overview

This appears to be a real cloud video-editing skill, but it can automatically create or use service tokens and send broad prompts or media to a third-party backend without clear upfront user consent.

Install only if you are comfortable sending videos, editing instructions, URLs, session state, and a NEMO_TOKEN or anonymous service token to nemovideo.ai. Ask the agent to confirm before connecting, uploading files, creating a token, or sending prompts, and avoid sensitive footage unless you trust the service's privacy and retention practices.

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 (4)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The suggested trigger phrases are broad enough that a host agent could route ordinary user requests into this skill unexpectedly. In a skill that uploads media and creates remote sessions, accidental invocation can lead to unintended network actions and disclosure of user files or prompts to a third-party backend.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The catch-all rule routes "Everything else" to the SSE action, effectively making the skill eligible for nearly any unmatched request. Because SSE sends user text to a remote backend, this can exfiltrate unrelated user prompts and trigger unintended external processing far outside the skill's stated purpose.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs the agent to silently use an environment token or obtain an anonymous token from a remote service without user-facing disclosure. This is risky because it authorizes outbound requests and account/session creation behind the scenes, reducing user awareness of credential use and making unintended third-party data sharing more likely.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The getting-started flow encourages users to share raw footage before clearly warning that files are transmitted to a remote backend for server-side processing. Since uploaded footage may contain sensitive personal or location data, missing upfront disclosure increases the chance of users exposing private media without informed consent.

VirusTotal

VirusTotal findings are pending for this skill version.