ClawHub

google-image-api-skill

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it uses a BrowserAct API key to fetch structured Google Images results, with privacy and setup cautions but no hidden or destructive behavior found.

Install only if you are comfortable sending image-search keywords, country/language settings, and related result metadata to BrowserAct and Google Images using your BrowserAct account. Avoid sensitive or confidential search terms, and use a dedicated or limited API key where possible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill uses environment variables and an external API/network capability, but does not clearly declare permissions for them. This weakens sandboxing and informed consent, because an agent may invoke the skill without an explicit security boundary around secret access and outbound data transmission. In this context, the skill sends search terms to BrowserAct/Google Images and depends on an API key, so undeclared capabilities materially increase risk.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description tells the agent to proactively apply this skill for a very broad set of common image-search and research requests. That can cause over-triggering, sending user queries and context to an external service without a clear, specific user request or consent. Because the skill is networked and uses a third-party API, broad invocation criteria increase the chance of unnecessary data disclosure.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The markdown does not warn users that their search terms and related query context will be transmitted to BrowserAct and indirectly to Google Images. Without this disclosure, users may unknowingly send sensitive topics, proprietary research terms, or personal data to third parties. The skill context makes this more dangerous because it encourages proactive use for market research and competitor monitoring, which can involve confidential business information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal