letta-development-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill's tool documentation (references/tool-patterns.md "Custom Tool Development" example) shows creating a custom tool that performs requests.get against a public URL (https://wttr.in) so agents can fetch and ingest arbitrary third‑party web content whose returned text is consumed as tool output and can influence agent decisions and subsequent tool use.