Back to skill

Security audit

Competitive Ads Extractor Pro

Security checks for vulnerabilities and agentic risk

Overview

This marketing-research skill is coherent and disclosed, with local saved ad screenshots as the main user-visible consideration.

Before installing, understand that this skill may browse public ad libraries and save screenshots, reports, CSVs, or decks on your machine. Use it for research and inspiration, keep outputs in a location you can review or delete, and avoid copying competitors' creative directly.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly states it will save screenshots and analysis files to local storage, but it does not clearly warn the user up front that files will be written or where they will be stored by default. This can lead to unexpected persistence of scraped third-party content, possible disk consumption, and inadvertent retention of sensitive or copyrighted material on the host system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.