ClawHub
Back to skill

Security audit

Amazon Fba Calculator

Security checks for vulnerabilities and agentic risk

Overview

This is a local Amazon FBA fee calculator with no hidden access or persistence, though users should verify the fee math before relying on it for business decisions.

Before installing, treat the output as an estimate and verify current Amazon fee rules and whether removal/disposal fees should be included in your scenario. The skill does not appear to access private data or make changes outside the local calculation.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The code defines a removal/disposal fee in the fee breakdown but never incorporates it into total fee calculations, creating a systematic understatement of total costs and overstating profit and ROI. In an FBA calculator, users may make pricing, sourcing, or inventory decisions based on inaccurate financial outputs, which is a genuine integrity issue even though it is not a code-execution flaw.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The front matter sets lang: en, which is a natural-language locale constraint in a file type covered by policy checks. Although the usage example later shows a --zh option, the manifest itself presents English as the fixed language and does not clearly state that users may choose another language or why English is required.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

Natural-language policy violations apply to all file types, including code string literals and UI behavior. This file exposes only English by default and Chinese through a special flag, but provides no documented user opt-in flow or justification for the locale behavior, which can conflict with organizational language-choice expectations.

Content

No source excerpt is available for this finding.