openrouter-api
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official SDKs for the OpenRouter service, including the
@openrouter/sdkand@openrouter/agentnpm packages and theopenrouterPython package. These are standard resources for interacting with the documented API.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of responses from external LLMs and web search tools via the OpenRouter API interface. - Ingestion points: Ingests untrusted data from
openrouter.aiAPI response payloads (chat completions and tool outputs). - Boundary markers: The instructions do not define specific delimiters or ignore-instructions for the processed external data.
- Capability inventory: Primarily performs network communication with the
openrouter.aidomain. - Sanitization: Does not specify methods for sanitizing or escaping the content retrieved from external LLMs or search engines.
Audit Metadata