Back to skill

Security audit

Openclaw Meta Ads

Security checks across malware telemetry and agentic risk

Overview

This is a docs-only Meta Ads analysis skill with disclosed credential use, read-first guidance, and approval required before live ad changes.

Install only if you are comfortable letting an agent inspect Meta Ads performance and, after explicit approval, potentially help with live account changes. Use read-only scopes where possible, keep tokens out of files and chat, and limit lead data exposure to the minimum needed for analysis.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal