ClawHub
Back to skill

Security audit

Meta Ads MCP

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Meta ads operations guide with clear approval, pause-first, and privacy guardrails.

Before installing, confirm you actually want an agent to help with Meta Ads operations and that any connected Facebook Ads MCP account has the right permissions. Review campaign changes before activation, set spending limits, and do not upload customer lists or send CAPI PII unless your organization has documented consent and hashing controls in place.

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
88% confidence
Finding
The skill advertises itself for a very broad set of common topics such as Facebook ads, budgets, audiences, retargeting, tracking, and documentation, without clear exclusion boundaries or stronger routing criteria. In an agent environment, this can cause over-invocation on loosely related requests, increasing the chance that the skill influences workflows it should not handle, especially where external systems and cross-skill dependencies are involved.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.