cloudflare

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and workflows explicitly show fetching and ingesting untrusted public content—e.g., browser rendering examples that call page.goto and scraping endpoints (references/browser-rendering/api.md & patterns.md), AI Search configuration that indexes Website data sources (references/ai-search/*), and Agents SDK examples that ingest email/web text and pass it to AI models (references/agents-sdk/api.md & patterns.md)—so the agent is expected to read/interpret third-party content that can materially influence actions.