ClawHub
Back to skill

Security audit

YG3 Marketing MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent marketing automation documentation, but it asks an agent to handle and send a human owner's password without enough safety guidance.

Review the credential claim step before installing. Use this skill only if you are comfortable with the agent provisioning a YG3 workspace and calling YG3 marketing APIs, and do not give it a reused password; prefer OAuth or a one-time/account-linking flow when available.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to send a human owner's email and password to an external API in a curl request, but provides no warning about secure credential collection, storage, consent, or handling. In an autonomous-agent context, this is dangerous because it normalizes password capture and transmission by the agent, increasing the risk of credential theft, logging leakage, reuse of user passwords, or collection without informed user approval.

Static analysis

No suspicious patterns detected.