ktx-ai-data-agents

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @kaelio/ktx package and its dependencies from the public NPM registry.
  • [COMMAND_EXECUTION]: The skill instructions involve executing several CLI commands such as 'ktx setup' and 'ktx ingest' which handle sensitive database configuration and environment variables.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from various external sources which is then processed by the LLM, creating a potential surface for indirect prompt injection. * 1. Ingestion points: Metadata and content from SQL databases (PostgreSQL, Snowflake, etc.), dbt projects, Notion pages, and business wikis. * 2. Boundary markers: Not explicitly defined in the provided skill instructions. * 3. Capability inventory: The skill provides tools for executing database queries, searching semantic layers, and fetching canonical SQL. * 4. Sanitization: The documentation does not detail specific sanitization or filtering protocols for ingested content.
  • [DYNAMIC_EXECUTION]: The configuration allows for custom database connectors to be defined in local TypeScript files (e.g., ./connectors/custom-db.ts), which are loaded and executed by the tool at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — ktx-ai-data-agents