letta-development-guide

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

• Third-party content exposure detected (high risk: 1.00). The skill includes a custom tool example that performs an HTTP GET to a public site (references/tool-patterns.md: the fetch_weather example calling https://wttr.in/{city}), which clearly fetches untrusted third-party web content that the agent would read and return as part of its workflow.