ktx-ai-data-agents-context
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from warehouse tables, dbt metadata, and Notion content to provide context to the LLM. This creates an attack surface where malicious content within those data sources could influence agent actions. Evidence: The ktx ingest command processes multiple external data streams.\n- [EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of an external NPM package @kaelio/ktx and the addition of a skill from the Kaelio/ktx GitHub repository. Evidence: Found in the Installation and Agent Integration sections.
Audit Metadata