ClawHub
Back to skill

Security audit

TikTok Ads Strategy: Creative-First Campaigns and Optimization

Security checks for vulnerabilities and agentic risk

Overview

The skill is a TikTok ads guide with a disclosed AdKit CLI execution path, but no hidden code, persistence, or destructive behavior was found.

Install only if you are comfortable with the agent checking for AdKit and preferring that CLI when you ask it to execute TikTok ad operations. Require explicit approval before any command changes campaigns, budgets, audiences, or account data.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The skill is ներկայացված as a TikTok advertising strategy guide, but the execution section redirects the agent into AdKit-specific operational steps. This is a scope mismatch that can mislead users and cause the agent to take vendor-specific actions unrelated to the advertised skill boundary, increasing the risk of unauthorized tool use or hidden product steering.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill goes beyond providing TikTok ads strategy guidance and instructs the agent to probe the local environment by running `adkit status`, then prefer an external vendor-specific CLI if present. That behavior is not necessary for the stated purpose and creates an unjustified execution path that can expand the skill's capabilities from advisory guidance into tool discovery and operational action.

Static analysis

No suspicious patterns detected.