openrouter-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports fetching and ingesting arbitrary third‑party content (e.g., the Web Search Plugin and :online model suffix in references/plugins-features.md, the web_search tool in references/responses-api.md, and external image/pdf URLs/file-parser usage in references/plugins-features.md and chat-completions.md), so the agent will read and interpret untrusted public web/user-generated content as part of its workflow.