ClawHub
Back to skill

Security audit

SportsDataIO

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SportsDataIO connector wrapper with minor documentation issues but no evidence of hidden, destructive, or unrelated behavior.

Install only if you intend to use an OOMOL-connected SportsDataIO account. Review payloads before running any tagged write action, and be aware that request parameters and payload data are sent through OOMOL to SportsDataIO.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
Two actions described as read-only schedule/list operations are tagged as `[write]`, which can mislead an agent into applying unnecessary or incorrect confirmation logic and obscures the true risk profile of the action set. Mislabeling operation safety is dangerous because it erodes operator trust in the skill’s safety guidance and can cause both overblocking of benign actions and underestimation of genuinely state-changing ones elsewhere.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The instruction to use this skill for ANY SportsDataIO request is overly broad and can cause an agent to invoke the connector automatically whenever SportsDataIO is mentioned, without first assessing whether external transmission is necessary or appropriate. In a skill that can perform state-changing actions through server-side credentials, broad routing language increases the chance of unintended data disclosure or unintended operations.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explains that OOMOL injects credentials server-side and supports creating and updating data, but it does not clearly warn that user-supplied payloads will be transmitted to an external third-party service under those credentials. That omission is dangerous because users and downstream agents may not realize they are causing external API calls and potential data sharing or account-side changes.

Static analysis

No suspicious patterns detected.