ClawHub
Back to skill

Security audit

Openrouter Free

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: list OpenRouter free models and send user-entered chat prompts to OpenRouter using an API key.

Install this only if you intend to use OpenRouter. Prefer providing OPENROUTER_API_KEY explicitly in the runtime environment or using a dedicated limited key, and avoid sending secrets, proprietary code, or private data in prompts unless you are comfortable with OpenRouter processing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill falls back to reading a hard-coded workspace .env file to obtain an API key, which expands its access from the explicit environment into local credential files. In an agent-skill context, this is risky because it silently reaches into local secrets storage without clear user consent and normalizes credential-file access beyond the minimum needed.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
Reading API credentials from a local .env file without informing the user is a security transparency problem. Users may assume the skill only uses supplied environment configuration, while it actually probes local secret storage and consumes credentials silently.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The chat function transmits user prompt content to an external third-party API without any explicit privacy warning or consent step. In a skill environment, prompts may contain sensitive user or workspace data, so undisclosed external transmission creates real confidentiality risk even if the endpoint is legitimate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.