Google Ads

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Google Ads skill, but it gives an agent broad ability to change or delete ad-account assets without clear built-in safety checks.

Install only if you trust Membrane and intend to let an agent manage Google Ads. Before any create, update, delete, budget, user, conversion-upload, or raw proxy request, verify the exact Google Ads customer account, action, endpoint, and payload, and require explicit human confirmation for destructive or spend-affecting changes.

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

Findings (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill advertises a destructive action ('Remove Campaign') without any warning, confirmation requirement, or guidance to verify ownership and intent before execution. In an agent setting, this increases the risk of accidental or unauthorized deletion of advertising assets, causing service disruption and financial loss.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal