ktx-ai-data-context-layer

Warn

Audited by Snyk on Jun 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.65). The required workflow includes ingesting “wiki content” and “context sources” (e.g., ktx ingest for wiki/Notion/dbt/Looker), which at runtime reads outsider-authored free-form text from those external systems (e.g., wiki pages or Notion database entries not authored by the operating user) and then feeds it into the agent’s LLM context via the built semantic layer/MCP tools.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 16, 2026, 10:19 AM
Issues
1
Security Audit — snyk — ktx-ai-data-context-layer