pydantic-ai

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

• Third-party content exposure detected (high risk: 0.90). The skill includes a concrete tool example in "Step 4: Tool Use" that fetches and parses data from the public URL https://wttr.in/{city}?format=j1 via httpx, so the agent reads and acts on untrusted third-party web content as part of its workflow.