Meta Video Ad Analyzer

• Outcome: Pass
• Latest audit: May 28, 2026, 5:44 AM
• Version:
  1.0.0

Overview

This skill does what it advertises: analyzes user-provided video or image ads with local media tools and Google AI services, with some privacy and deployment cautions.

Install in an isolated environment, use a dedicated least-privilege Google service account, and analyze only media you are allowed to send to Google cloud services. In shared deployments, keep generated thumbnails out of public access or add authenticated serving and unique filenames.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

audio_path = temp_f.name

            try:
                subprocess.run([
                    'ffmpeg', '-i', video_path, '-vn', '-f', 'wav',
                    '-acodec', 'pcm_s16le', '-ar', '16000', '-ac', '1',
                    '-y', audio_path

• Confidence: 85% confidence
• Finding: subprocess.run([ 'ffmpeg', '-i', video_path, '-vn', '-f', 'wav', '-acodec', 'pcm_s16le', '-ar', '16000', '-ac', '1', '-y', a

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill documentation describes capabilities that require environment access, local file reads, and shell-adjacent tooling such as ffmpeg, but it does not declare permissions accordingly. This creates a transparency and policy-enforcement gap: an agent or user may invoke a skill with broader access than expected, increasing the risk of unintended file exposure or command execution through supporting scripts.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill sends video frames, images, and audio-derived content to external Google AI services for scene analysis and transcription, but the description does not warn users that potentially sensitive media leaves the local environment. This can lead to privacy, confidentiality, and compliance issues if users analyze ads or videos containing personal data, unreleased creative, or regulated content without informed consent.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill sends extracted frames, full images, and potentially full video/audio content to external AI and speech services without any explicit consent gate, policy check, or user-visible disclosure in the operational code path. In a media-analysis context, those inputs may contain sensitive, copyrighted, regulated, or internal material, so silent third-party transmission creates a real data-exposure risk.

VirusTotal

64/64 vendors flagged this skill as clean.