ktx-ai-data-context-layer

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes several TypeScript utility scripts that use child_process.execSync to interact with the ktx CLI tool for project initialization, automated data ingestion, and context searching.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest external data—including wiki content, dbt models, Notion pages, and database metadata—to provide context for AI agents. This creates a surface for indirect prompt injection if the ingested sources contain malicious instructions designed to influence the agent.
  • Ingestion points: Data is gathered via the ktx ingest command from various sources specified in the ktx.yaml configuration, including local markdown files and external third-party APIs like Notion and Metabase.
  • Boundary markers: The current documentation and configuration do not specify the use of delimiters or explicit 'ignore' instructions when presenting search results to the agent's context.
  • Capability inventory: The skill environment allows for command execution via local scripts and provides extensive tools for detailed schema and metric inspection.
  • Sanitization: There is no evidence of content sanitization or filtering logic designed to prevent the agent from executing instructions embedded within the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — ktx-ai-data-context-layer