letta

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly enables agents to perform web searches and web scraping (see "Built-in Tools" listing the web_search tool) and to run code with network access including "web scraping" (see "Second execution (separate-run_code-call)" and examples mentioning requests + BeautifulSoup), meaning the agent will fetch and interpret untrusted public web content as part of its workflow.