Meta Ads Report Skill

• Outcome: Pass
• Latest audit: May 27, 2026 at 10:45 PM UTC
• Version:
  1.0.0

Overview

This skill appears to be a straightforward Meta Ads reporting tool that reads user-provided Meta credentials to fetch ad metrics and event names.

Install only if you are comfortable giving the skill read access to the specified Meta Ads account. Use a least-privilege Meta token with ads_read/read_insights, keep it out of chat logs and version control, rotate it if exposed, and consider pinning dependencies before deployment.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README instructs users to place a powerful Meta access token in a local .env file but provides no warning that this value is a sensitive credential, should not be committed to source control, and should be rotated if exposed. In an agent-skill context, this increases the chance of accidental credential leakage through repository commits, logs, screenshots, or support sharing, which could grant unauthorized read access to ads data.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill documentation instructs users to supply a Meta access token and ad account identifier but provides no guidance on secure storage, least-privilege token handling, rotation, or the sensitivity of ad account analytics and event data. This can lead users to paste long-lived credentials into insecure environments or expose account-level marketing data without understanding the privacy and operational risks.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill reads a Meta access token and ad account ID from environment variables and then uses them to make external API calls, but the user-facing interface does not disclose that credentials will be used or that data will be sent to Meta. In an agent setting, this creates a transparency and consent problem because a user may trigger external account access without understanding the action scope.

VirusTotal

64/64 vendors flagged this skill as clean.