ClawHub
Back to skill

Security audit

Amz Product Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This Amazon listing optimization skill is coherent and disclosed, but users should understand it may modify product files, use external services, and optionally schedule CTR monitoring.

Before installing, confirm you are comfortable with a skill that can update your product JSON/CSV file, generate image prompts through Taobao MCP, scrape keyword sources, and optionally set up daily CTR monitoring. For important business data, ask it to create a backup or write to a new output file first.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The top-level description is broad enough to match generic requests about optimization, images, titles, monitoring, and automation, which can cause the skill to be invoked in situations the user did not clearly intend. In this skill, unintended invocation is meaningful because the workflow includes file writes, scraping, and optional scheduled monitoring, so a loose trigger surface increases the chance of unintended side effects.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The workflow includes scraping hot keywords and generating images via an external service, but the skill does not clearly disclose that product data, prompts, or related metadata may be transmitted to third parties. This creates privacy, compliance, and data-handling risks, especially for proprietary listing data or business-sensitive product information.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it updates and saves results back to the supplied product file, but the user-facing description and examples do not clearly warn that execution is state-changing. That can lead to silent modification or corruption of local business data if the skill is invoked unexpectedly or without an explicit confirmation step.

Static analysis

No suspicious patterns detected.