ktx-data-agent-context-layer

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs users to install a CLI tool via NPM (npm install -g @kaelio/ktx) and execute various management commands (e.g., ktx ingest, ktx setup, ktx mcp start). These commands are necessary for the tool's core functionality of building a data context layer.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the @kaelio/ktx package from the official NPM registry and fetches data from user-configured external sources such as Notion, Looker, and Metabase to build the context layer. These operations are consistent with the skill's stated purpose.
  • [CREDENTIALS_UNSAFE]: The documentation provides examples of how to configure database credentials and API keys. It correctly advises users to store these secrets in environment variables or a local .ktx/secrets.yaml file that is git-ignored, preventing accidental exposure in version control.
  • [DATA_EXFILTRATION]: While the tool connects to external databases and APIs, these connections are made to legitimate, user-defined endpoints for the purpose of metadata ingestion and querying. There is no evidence of unauthorized data transfer to unknown domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:04 AM
Security Audit — agent-trust-hub — ktx-data-agent-context-layer