Meta Ads Analytics

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only Meta Ads analytics helper that can read and export ad performance data through a named MCP, with no executable code or hidden setup.

Install this only in environments where brijr/meta-mcp is trusted and scoped to the Meta Ads accounts you intend to analyze. Review exported insights before sharing, since they may include spend, campaign structure, creative details, and performance metrics.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill can activate for very broad requests like performance analysis, reporting, or explaining changes, which overlap with many generic analytics tasks. Ambiguous activation boundaries increase the chance the agent invokes this skill in the wrong context, leading to unnecessary access to advertising account data or analytics outputs beyond what the user specifically intended.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal