ktx-ai-data-agents
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @kaelio/ktx package from the NPM registry. This is a functional requirement for the project operation.
- [COMMAND_EXECUTION]: Users are instructed to run various ktx and npx commands for setup, data ingestion, and starting an MCP server. It also supports loading custom connector scripts from local paths, which is a standard extensibility feature.
- [PROMPT_INJECTION]: The skill ingests data from external sources like Notion, dbt, and local wikis, creating a surface for indirect prompt injection. 1. Ingestion points: dbt projects, Notion pages, and markdown wiki files. 2. Boundary markers: Not explicitly implemented in the provided instructions. 3. Capability inventory: Includes database query execution, network ingestion, and local state management. 4. Sanitization: Relies on contradiction detection for data integrity but lacks specific security sanitization for external content.
Audit Metadata