ktx-ai-data-agents-mcp-context-skills

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @kaelio/ktx package via npm to provide the underlying CLI and MCP functionality.
  • [COMMAND_EXECUTION]: Uses shell commands such as ktx ingest, ktx setup, and ktx mcp start to manage data context and interface with the agent.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.
  • Ingestion points: Ingests data from several external sources including dbt, Notion, Metabase, and various databases as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are mentioned to prevent the agent from following instructions embedded in the ingested data.
  • Capability inventory: The skill exposes tools to the agent (ktx_search_semantic_layer, ktx_search_wiki) that retrieve and display potentially untrusted content from the ingested sources.
  • Sanitization: The documentation does not describe any sanitization or validation processes for data fetched from external connections.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:04 AM
Security Audit — agent-trust-hub — ktx-ai-data-agents-mcp-context-skills