ClawHub
Back to skill

Security audit

Amazon PA-API Integration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Amazon PA-API helper whose disclosed behavior matches product search and product lookup use.

Before installing, confirm you intend to use Amazon Germany PA-API and are comfortable providing Amazon PA-API credentials and a partner tag through environment variables. No hidden execution or persistence was found in the artifact.

A.I.G

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

SkillSpector

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)

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The description says the skill searches products on Amazon.de, which imposes a specific locale/marketplace behavior in natural language. The file does not state that this is optional, user-selectable, or justified as a region-specific skill, so it may violate language/locale policy expectations.

Static analysis

No suspicious patterns detected.