ClawHub
Back to skill

Security audit

Google Ads

Security checks for vulnerabilities and agentic risk

Overview

This Google Ads skill is broad but its sensitive actions are disclosed, scoped to user-approved Maton/Google Ads connections, and guarded by explicit approval instructions.

Before installing, be comfortable that this skill can operate on Google Ads business data and can help create persistent automations if you approve them. Use read-only queries first, confirm every write or connection, avoid third-party trigger destinations unless you explicitly trust the host, and prefer the CLI OAuth flow over raw API keys.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The Google Ads manifest says the skill is for interacting with Google Ads data and explicitly states Google Ads is not an event source, while this file documents HubSpot event types, parameters, and payloads in detail. Even though the preamble tries to limit interpretation, the file's substantive content still describes capabilities for a different third-party app than the skill claims to cover.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.