langchain-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples explicitly invoke web/search and scraping tools (e.g., tools=[search, scrape], subagents with "news" and "social" strategies, and structured outputs containing source URLs) and the agent workflows ingest and summarize those external web/social results, so it clearly consumes untrusted third-party content that could carry indirect prompt injections.