ClawHub
Back to skill

Security audit

Deep Ads Analyst

Security checks for vulnerabilities and agentic risk

Overview

This is a plain advertising-analysis guidance skill with no executable code, data access, persistence, or hidden behavior.

Installers should understand this skill may be selected for broad growth or revenue questions, so it is best used when the task is clearly about paid advertising analysis or ad-platform strategy. It does not appear to access accounts or change campaigns by itself.

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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation conditions are broad and describe general business outcome requests without sufficiently constraining when the skill should not be used. In a multi-skill agent, this can lead to over-selection of this skill for ambiguous prompts, causing cross-platform ad-analysis behavior to be applied where it is not warranted and increasing the risk of incorrect guidance or context leakage between tasks.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger keywords include very common business and marketing terms such as "growth," "revenue," "profit," and "campaign," which can cause the skill to activate for many unrelated requests. Over-broad activation increases the chance this specialized skill overrides more appropriate skills or injects domain-specific assumptions into general business conversations, reducing reliability and potentially causing unsafe or misleading recommendations in downstream workflows.

Static analysis

No suspicious patterns detected.