Security audit
GoBuy the Trust Layer for Agentic Commerce
Security checks for vulnerabilities and agentic risk
Overview
The skill’s shopping-evidence checks and disclosed caller tracking fit its stated purpose, with no harmful local behavior found.
Use this if you accept sending shopping queries and disclosed caller identifiers to GoBuy. Treat scores as evidence signals, not safety guarantees or purchase authorization. The full artifact was reviewed despite the scanner’s frontmatter parsing gap; hosted-service privacy practices remain unverified.
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
