ClawHub
Back to skill

Security audit

Ads Account Health

Security checks for vulnerabilities and agentic risk

Overview

This advisory ad-account health skill is coherent and contains no executable code, but users should treat its budget and campaign recommendations as business-impacting guidance.

Install only if you want advisory help reviewing advertising account readiness and campaign risks. Before applying any budget, bidding, billing, policy, or launch recommendation to a real account, verify the source data, platform permissions, compliance constraints, and rollback plan.

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
  • 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 (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill does not clearly warn that its recommendations may influence live advertising spend, campaign settings, billing exposure, or account health. Without an explicit caution, users or downstream agents may treat outputs as low-risk analysis rather than guidance that could lead to costly changes or policy/account consequences when applied operationally.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger conditions are broad enough to match many generic marketing, growth, and performance-analysis requests, which can cause the skill to be invoked outside its intended scope. In an agent system, overbroad routing increases the chance that users receive execution-oriented ad-account guidance without sufficient platform context, permissions validation, or safety checks around live spend and account changes.

Static analysis

No suspicious patterns detected.