upstash/workflow TypeScript SDK Skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly shows ingestion of open/public third‑party content — e.g., a WikipediaQueryRun tool in agents.md and multiple APIs like context.call, client.trigger, context.createWebhook / waitForWebhook that fetch or accept arbitrary external URLs/requests — so the agent will read and act on untrusted user-generated or public web content.