Open Router

Security checks across malware telemetry and agentic risk

Overview

This is a transparent OpenRouter setup skill whose API-key use, OpenRouter network calls, and local routing notes match its stated purpose.

Install only if you are comfortable using OpenRouter for routed model requests, since prompt content may be sent to OpenRouter and usage may incur cost. Keep OPENROUTER_API_KEY in the environment rather than chat, avoid putting secrets in ~/open-router/, and review or delete those local notes if your routing preferences change.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The Activation section defines broad trigger categories such as auto-activate, explicit-only topics, and never activate for, but provides no schema, validation rules, or safety boundaries. In an agent skill, underspecified activation criteria can cause the skill to trigger in unintended contexts, leading to misapplied routing behavior, unnecessary provider use, or disclosure of operational context when the user did not intend to invoke this capability.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal