openrouter-multi-provider

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill serves as a legitimate technical guide and template library for multi-provider AI integration.
  • [EXTERNAL_DOWNLOADS]: Accesses the OpenRouter API (openrouter.ai) to retrieve model metadata and pricing information. This is a well-known service used for its intended purpose.
  • [DATA_EXFILTRATION]: Uses environment variables (e.g., OPENROUTER_API_KEY) for secret management, which is the standard and safe method for providing credentials to agentic workflows.
  • [PROMPT_INJECTION]: The skill contains logic to process and compare responses from multiple AI models. While this represents a data ingestion surface (Indirect Prompt Injection), the provided code snippets handle model outputs for analysis and display purposes only, without performing unsafe operations based on the model content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 09:42 PM
Security Audit — agent-trust-hub — openrouter-multi-provider