ktx-ai-data-agents-context

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow for “serves agents at execution” via the MCP tools (e.g., ktx_search_wiki / ktx_search_semantic_layer) can ingest and return wiki content and other configured context sources (Notion/wiki/dbt docs) that are not authored by the operating user, and that returned free text is then placed into the agent’s LLM context through the MCP tool responses.