ClawHub
Back to skill

Security audit

Openrouter Models Pricing

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward OpenRouter model-pricing helper that fetches a public catalog and analyzes a local cached copy.

Before installing, understand that refreshing data will contact OpenRouter and write a local JSON cache. Do not provide an OpenRouter API key unless you want requests attributed to your account; the public endpoint works without one.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation instructs users to run local Python scripts that perform network access and write files, but the skill declares no corresponding permissions. This mismatch is dangerous because it hides the true capability surface from reviewers and runtime policy systems, increasing the chance that users execute code with broader access than expected.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.