research

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

• Third-party content exposure detected (high risk: 1.00). This skill's bundled Tavily CLI (scripts/tavily-cli.ts) calls Tavily's web-search API (https://api.tavily.com/search) and can retrieve and print raw page content and AI summaries from arbitrary public websites (e.g., via the --raw and printed results), meaning the agent will ingest untrusted third-party web content.