skills/jeremylongshore/claude-code-plugins-plus-skills/openrouter-streaming-setup/Gen Agent Trust Hub
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
promptvariable 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