agents-sdk

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this skill is to fetch Cloudflare Agents SDK documentation from GitHub (public web content) and/or use that fetched text as context; this is an outsider source (public web pages) ingested into the agent’s LLM context via the runtime docs-fetch path.