letta-api-client

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly enables and demonstrates a built-in "web_search" tool (e.g., tools=["web_search"] in examples/02_create_agent.py and examples/05_send_message.py and in custom-tools.md), which causes the agent to fetch and interpret arbitrary public web/search results (untrusted third‑party content), creating a clear avenue for indirect prompt injection.