Back to skill

Security audit

Shop Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only shopping research helper that uses the Portage CLI to look up products, stores, and the user's Portage history without purchasing anything.

Install this only if you are comfortable letting Portage perform product and store lookups and read your Portage search/order history. Optional API keys should be entered only in your local Portage config, not pasted into chat, and buying should be handled by a separate purchase flow with approval.

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