ClawHub
Back to skill

Security audit

InferSports

Security checks across malware telemetry and agentic risk

Overview

This skill coherently provides read-only sports odds and score lookups through disclosed local scripts and the InferSports API.

Install only if you are comfortable with a skill running bundled bash scripts that call the InferSports API. Leave INFERSPORTS_API_KEY unset for free-tier use, and set INFERSPORTS_API_BASE only to a host you trust because the optional API key would be sent there.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill explicitly instructs the agent to run bundled shell scripts and those scripts perform network access, yet the skill declares no permissions. That creates a capability/visibility mismatch: an operator or policy engine may treat the skill as lower risk than it really is, while execution still reaches shell and external network resources.

Intent-Code Divergence

Medium
Confidence
80% confidence
Finding
The documentation markets the skill as 'keyless' and requiring no API key, but later introduces optional API-key use and access to a 'sharp book.' This inconsistency can mislead reviewers and users about authentication, data-scope, and privilege assumptions, causing the skill to be approved or used under an inaccurate trust model.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal