ClawHub
Back to skill

Security audit

Amazon Listing Optimization

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public Amazon listing pages to help generate or audit listing copy, and the reviewed artifacts do not show hidden credential use, persistence, destructive behavior, or unrelated data collection.

Install only if you are comfortable with live Amazon and web-search requests for the ASINs, URLs, keywords, and marketplaces you provide. Avoid entering product plans or competitor targets you consider confidential, verify the GitHub source before installing, and review generated listing copy before using it in Seller Central.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs use of a bundled shell script (`fetch-listing.sh`) but declares no permissions, creating a transparency and governance gap. Hidden shell capability increases risk because operators may approve or run the skill without understanding that it executes local commands and performs network retrieval against user-supplied ASINs/URLs.

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding
The published description frames the skill as a listing optimizer, but the body also directs scraping Amazon product pages and extracting metadata via shell/web fetch. This mismatch is dangerous because it obscures data collection and network behavior from users and reviewers, weakening trust boundaries and making risky functionality easier to smuggle into an apparently benign marketing tool.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.