ClawHub
Back to skill

Security audit

World Bank API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward World Bank data helper that makes disclosed, purpose-aligned public API requests and does not show hidden data access, persistence, or destructive behavior.

Install this if you are comfortable with your macroeconomic or development-data queries being sent to the public World Bank API. Consider narrowing use to tasks where live World Bank data is desired, since the skill's trigger wording may cause agents to use it even when the user did not explicitly name World Bank.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill clearly instructs the agent to perform outbound network requests, but the metadata shown does not declare corresponding permissions. Undeclared network capability weakens transparency and policy enforcement because a host system or reviewer may not realize the skill can transmit prompts or user-supplied parameters to an external service.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The description says to use this skill for any macroeconomic statistics, country comparison, development indicator, or historical country data task even when the World Bank is not mentioned, which creates an overly broad trigger surface. That can cause unintended invocation and external requests in contexts where the user did not expect data fetches or where another safer/local capability would have been more appropriate.

Static analysis

No suspicious patterns detected.