devextreme-datagrid

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill documents AI-integrated features (AI Columns and AI Assistant) that process grid data via LLMs. While this creates an indirect prompt injection surface, the documentation includes security-focused instructions and specific event hooks (onAIColumnRequestCreating, onAIAssistantRequestCreating) to filter and restrict data sent to external services, mitigating potential injection risks.
  • [EXTERNAL_DOWNLOADS]: The skill references official DevExtreme modules and established libraries (exceljs, jspdf, file-saver) hosted on reputable CDNs such as jsDelivr and Cloudflare. These are standard, well-known resources for implementing export and AI features.
  • [COMMAND_EXECUTION]: The skill provides instructions for using the devexpress_docs_search MCP tool to retrieve official API documentation. The provided guidance instructs the agent to treat fetched text as reference material only, protecting against potential instruction-based attacks embedded in external documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 01:48 PM
Security Audit — agent-trust-hub — devextreme-datagrid