Back to skill

Security audit

GoBuy the Trust Layer for Agentic Commerce

Security checks for vulnerabilities and agentic risk

Overview

The skill’s shopping-trust checks and disclosed caller tracking fit its purpose, with no bundled executable code or hidden local access.

GoBuy receives your lookup targets and discloses pseudonymous caller tracking. Treat scores as evidence signals, not guarantees or permission to spend. Correct the frontmatter before installation and review the hosted service’s privacy terms; its implementation was not included for inspection.

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