building-ai-agent-on-cloudflare

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs retrieval from public sites (SKILL.md "Prefer retrieval" linking to GitHub and developers.cloudflare) and the ToolAgent example in references/agent-patterns.md performs fetches to external URLs (e.g., fetch("https://api.weather.com/...")) whose results are fed back into the AI/tool workflow, so untrusted third-party content can directly influence agent actions.