openrouter
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with the official OpenRouter API (openrouter.ai), which is a well-known service for accessing large language models.
- [SAFE]: API credentials are handled securely via the OPENROUTER_API_KEY environment variable, following standard practices for managing sensitive secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill manages an attack surface for indirect prompt injection through its primary functionality.
- Ingestion points: Processes user input via the
--promptargument and external model responses from the OpenRouter API in thechatcommand. - Boundary markers: No explicit delimiters or instructions are used to separate user data from system prompts.
- Capability inventory: Capabilities are restricted to network communication with the OpenRouter API and console output.
- Sanitization: Data is handled as structured JSON during transmission; the skill does not execute code or write to the file system based on input.
Audit Metadata