agent-search-optimisation

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

• Third-party content exposure detected (high risk: 0.85). The required workflow instructs the agent to fetch and crawl outsider-provided public website surfaces (e.g., robots.txt, sitemap.xml, llms.txt, and representative pages) and then use their readable text in the LLM context, creating an indirect prompt-injection exposure path via runtime web content ingestion.