openrouter-streaming-setup

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates best practices for sensitive data management by utilizing environment variables (e.g., OPENROUTER_API_KEY) rather than hardcoding credentials.
  • [SAFE]: Network communications are directed to a well-known service (OpenRouter.ai) and local application endpoints, following standard API implementation patterns.
  • [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation techniques were detected in the provided code snippets or documentation.
  • [INDIRECT_PROMPT_INJECTION]: As with any skill that processes user-generated text for LLM completion, there is a theoretical surface for indirect prompt injection.
  • Ingestion points: The prompt variable used in FastAPI, Express, and Python snippets.
  • Boundary markers: None implemented in the basic templates (common for educational code).
  • Capability inventory: The skill environment allows file writes and bash execution.
  • Sanitization: None applied to the prompt content before transmission to the model. Users should implement their own validation for production use.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 09:34 PM
Security Audit — agent-trust-hub — openrouter-streaming-setup