ClawHub
Back to skill

Security audit

Ads Media Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a guidance-only advertising media strategy skill with no executable code, hidden behavior, or privileged access.

Before installing, understand that this skill may be invoked for some broad growth or revenue discussions and may frame the answer around advertising strategy. It is otherwise low risk: it does not run code, install dependencies, access accounts, spend budgets, or persist 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
  • 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 (1)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger keywords include very broad business terms such as 'growth', 'revenue', 'profit', 'traffic', and 'conversion', which can cause the skill to activate for general business or analytics requests outside its intended advertising-planning scope. Overbroad invocation increases the chance of misrouting user requests to a specialized skill that may produce channel-specific ad guidance when a different skill or a narrower clarification step would be safer and more accurate.

Static analysis

No suspicious patterns detected.