ClawHub
Back to skill

Security audit

Ads Campaign Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain instruction guide for monitoring ad campaign incidents and does not contain code, persistence, credential handling, or hidden behavior.

This appears safe to install for ad operations workflows. Users should still avoid sharing unnecessary sensitive campaign data or owner contact details, and should treat recommendations such as pausing or containment as guidance to review before taking action in an ad platform.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are broad enough to capture many generic business, growth, and revenue-related requests that are not specifically about real-time campaign monitoring. This can cause the agent to invoke the wrong skill inappropriately, leading to irrelevant guidance, confusion, or unsafe operational recommendations in contexts where more specialized validation is needed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.