openrouter-trending-models

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill fetches and parses live data from OpenRouter's public rankings and Models API (https://openrouter.ai/rankings and https://openrouter.ai/api/v1/models), and the agent is expected to read and act on that untrusted public web/API content as part of its workflow, which could enable indirect prompt injection.