ClawHub
Back to skill

Security audit

Amazon Review Intelligence Extractor

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ARI command-line helper for Amazon review collection and analysis, with expected API-key and paid-credit handling protections.

Install only if you intend to use ARI and are comfortable giving this local CLI access to your ARI API key and sending ASIN/review-analysis requests to ARI. Prefer ARI_API_KEY if you do not want a saved local key, and review credit quotes before approving any command with --confirm.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to use shell commands, read/write local files for configuration, access environment variables for `ARI_API_KEY`, and make network requests, but it does not declare permissions. This creates a real security and governance gap: the runtime may grant capabilities implicitly without clear user visibility or policy enforcement, increasing the risk of secret exposure, unintended external calls, or unauthorized local state changes if the skill is misused or modified.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
README.md:99