Security audit

Ntriq World Bank Economic Indicators

Security checks for vulnerabilities and agentic risk

Overview

This is a simple World Bank data API skill, but users should notice it is pay-per-use despite prominent “Free” wording.

Before installing, treat this as a paid micropayment API rather than a free data source. Use it only if you are comfortable with the external endpoint and with agents making $0.01 USDC payments per call when you direct them to use it.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill markets the API as 'Free' and 'No subscription required' without clearly warning in the main description that each call requires a $0.01 USDC micropayment. This can mislead users or downstream agents into unexpected paid usage, especially in automated workflows that may assume zero-cost access from the description alone.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.