ClawHub
Back to skill

Security audit

Ads URL Parser

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ads-planning URL parser with no code execution, persistence, credential use, or account-changing behavior.

Before installing, expect this skill to help turn a URL and business goal into an ads launch brief. Review any budget, tracking, or channel recommendations before acting on them in real ad platforms, especially because broad ads-related prompts may activate the skill even when you wanted general marketing advice.

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 substantially broader than the skill's stated purpose of URL parsing and launch brief generation. Terms like ads, growth, revenue, profit, roi, budget, and platform names can cause the skill to activate for general marketing strategy conversations, leading to incorrect routing, over-collection of user inputs, or inappropriate ad-execution guidance outside its validated scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.