Back to skill

Security audit

buy

Security checks for vulnerabilities and agentic risk

Overview

This shopping skill is high-impact because it can help buy items, but its instructions consistently require Portage, dry runs, exact-total approval, and user-controlled setup before any purchase.

Install only if you trust the Portage CLI and are comfortable configuring shopping credentials locally. Keep approval required, set spending caps before real purchases, avoid pasting secrets into chat, and review each exact total and merchant before approving.

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