syncfusion-aspnetcore-inline-ai-assist

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a legitimate technical guide for the Syncfusion ASP.NET Core Inline AI Assist control. All referenced resources, including CDN endpoints and package names, are consistent with official Syncfusion infrastructure and branding.
  • [EXTERNAL_DOWNLOADS]: The documentation instructs developers to download and integrate resources from trusted locations:
  • Fetches the official Syncfusion.EJ2.AspNet.Core package from the NuGet registry as described in getting-started.md.
  • Loads client-side styles and scripts from Syncfusion's official CDN (cdn.syncfusion.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from the application's document, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: The control reads content from DOM elements (e.g., #editableText contenteditable div) and user input from the prompt textarea, as documented in SKILL.md and inline-assist-features.md.
  • Boundary markers: The provided implementation examples do not include explicit instructions for using delimiters or boundary markers to isolate processed content.
  • Capability inventory: The documented control has capabilities to perform network requests (via fetch in events-and-handlers.md) and modify the application's DOM structure (via innerHTML in response-settings-templates.md).
  • Sanitization: Implementation snippets demonstrate direct interpolation of AI-generated responses into the DOM using innerHTML without explicit sanitization, which is an architectural risk factor for the hosting application, although it aligns with the primary functional purpose of the AI Assist component.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 01:23 PM