ktx-context-layer-data-agents

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions direct the user to install the third-party package @kaelio/ktx via npm, which is an external dependency not managed by a verified well-known service.
  • [COMMAND_EXECUTION]: The skill requires the execution of multiple CLI commands (ktx setup, ktx ingest, ktx mcp start) that perform file system operations and network communication with database providers.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge between untrusted external data sources and the AI agent's context.
  • Ingestion points: Data is ingested from database schemas (Postgres, Snowflake, BigQuery, etc.), dbt manifests (manifest.json), and Notion pages.
  • Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are provided in the skill instructions to delimit the ingested data from the system prompt.
  • Capability inventory: The ingested context is used to execute SQL queries and search business metrics through an MCP server interface.
  • Sanitization: The instructions do not mention any sanitization or validation of the ingested metadata (such as table descriptions or wiki content) before it is provided to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — ktx-context-layer-data-agents