Back to skill

Security audit

Premier League Scores

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Premier League score lookup tool that fetches public ESPN data and prints it locally.

Install this only if you are comfortable with the skill contacting ESPN when you run it; ESPN will receive normal request metadata such as your IP address and User-Agent. I found no evidence that it accesses local data, stores anything, or changes your system.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill documentation indicates it fetches live data from ESPN over the network, but the manifest does not declare any explicit tool scope or permissions for network access. This creates a governance and least-privilege gap: a runner may allow broader capability than intended, and reviewers or policy engines cannot clearly validate that outbound network use is expected and constrained.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This code performs an outbound HTTP request to ESPN using urllib without any runtime notice to the user about contacting an external service. Although the module docstring names the ESPN API, there is no user-facing prompt or warning at the point of execution that the skill will transmit request metadata such as IP/User-Agent to a third party.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.