Meta Ads CLI

• Outcome: Review
• Latest audit: May 29, 2026 at 9:32 PM UTC
• Version:
  1.0.0

Overview

This Meta Ads reporting skill is coherent, but it relies on an unpinned external CLI with broad Meta OAuth access and can retrieve sensitive lead submissions without enough privacy guidance.

Review the external `meta-ads-open-cli` package and publisher before installing, preferably pinning a trusted version. Use the narrowest Meta token possible, avoid storing or pasting tokens in chat, shell history, screenshots, or shared files, and retrieve lead submissions only when authorized with a clear business need; redact or summarize personal data by default.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly documents retrieval of lead form submissions, which can contain personally identifiable information such as names, emails, phone numbers, and other submitted answers, but provides no warning or handling guidance for sensitive data. In a data-access skill, omission of privacy safeguards increases the chance the agent will retrieve, expose, summarize, or mishandle personal data without user confirmation or minimization.

VirusTotal

65/65 vendors flagged this skill as clean.