ktx-ai-data-agents-context

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the @kaelio/ktx package from the NPM registry and to fetch skill configurations from the Kaelio/ktx repository.
  • [COMMAND_EXECUTION]: The skill uses the ktx CLI tool to perform setup tasks, ingest data warehouse metadata, and run an MCP (Model Context Protocol) server for agent interaction.
  • [CREDENTIALS_UNSAFE]: The skill manages sensitive credentials including database passwords and AI provider API keys (e.g., ANTHROPIC_API_KEY). It demonstrates safe practice by instructing users to store these in environment variables or git-ignored local files like .ktx/secrets.yaml.
  • [PROMPT_INJECTION]: The skill functions by ingesting external business data from Notion, dbt, and databases to build context. This introduces a surface for indirect prompt injection if malicious instructions are embedded in the source documentation, though this is inherent to the skill's primary purpose of data context provisioning.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:19 AM
Security Audit — agent-trust-hub — ktx-ai-data-agents-context