add-top-openrouter-models

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent (SKILL.md and README) to open and scrape the public OpenRouter app leaderboard at https://openrouter.ai/apps?... and to query the OpenRouter API (/api/v1/models) for verification, and those externally-sourced model IDs are directly used to decide which local config files to update and whether to restart the gateway, so untrusted third-party content can influence behavior.