ClawHub
Back to skill

Security audit

zoomeye-ai-search

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent ZoomEye search helper, but it tells users to paste a ZoomEye API key into chat so the agent can configure it.

Install only if you want an agent to help with ZoomEye searches. Do not paste your ZoomEye API key into chat; configure it locally yourself with the CLI or a secret/environment mechanism, then tell the agent setup is complete. Rotate the key if you already exposed it, and confirm searches before running large queries that may use quota.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill explicitly tells the user to send their ZoomEye API key to the agent so the agent can initialize the CLI on the user's behalf. That is a real secret-handling flaw: API keys are credentials, and collecting them in chat exposes them to logging, retention, misuse, and accidental disclosure beyond the user's local environment. In this context, the skill is more dangerous because it is an agent workflow for security research tooling, where users may be accustomed to sharing operational details and may not realize the credential risk.

Ssd 3

Medium
Confidence
95% confidence
Finding
The skill directs the agent to solicit the user's API key and then act using that credential, which violates least-privilege and safe secret-handling practices. Even if intended for convenience, this creates unnecessary credential exposure and grants the agent the ability to use the user's account and quota, potentially causing unauthorized searches, quota depletion, or downstream compromise if the key is leaked.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.