tavily-hikari-research

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls the tvly-hikari research CLI (and follow-up status/poll) which, at runtime, fetches and returns web research content from Tavily/Hikari into the agent context as free-form text (public web content category via runtime tool output).