ClawHub
Back to skill

Security audit

Amazon Ads Reporter

Security checks across malware telemetry and agentic risk

Overview

This skill uses disclosed Amazon Ads credentials to fetch reporting and keyword bid data, with no evidence of hidden persistence, destructive changes, or unrelated data sharing.

Install only if you intend to let these scripts use your Amazon Ads OAuth credential file for the configured advertising profile. Review the credential scope, expect Amazon network calls, treat the current implementation as EU-focused, and do not rely on the documented campaign-level commands unless those missing scripts are supplied and reviewed.

SkillSpector

By NVIDIA
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

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.exposed_secret_literal

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/keyword-report.js:9

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/keyword-report.js:23