notemdpro-content-generator

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

• Third-party content exposure detected (high risk: 0.90). The generateContentForTitle flow explicitly calls _performResearch -> provider.search -> fetchContentFromUrl (with searchProvider options like 'duckduckgo' or 'tavily') and inserts the resulting {RESEARCH_CONTEXT_SECTION} into the LLM prompt, so arbitrary public web content can be ingested and influence downstream generation.