syncfusion-maui-smart-text-editor
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents the implementation of an AI-powered text editor that processes user-supplied input to generate completions.
- Ingestion points: The
SfSmartTextEditorcontrol, described inSKILL.md, accepts multiline text input from the user. - Boundary markers: While the
UserRoleproperty (documented inreferences/getting-started.md) allows setting the tone and intent for the AI, the documentation does not demonstrate the use of delimiters or explicit boundary markers to separate user input from system prompts. - Capability inventory: The skill documents sending user text to external AI services using
IChatClient(references/ai-service-configuration.md) or customHttpClientrequest logic (references/custom-ai-services.md). - Sanitization: No explicit examples of input validation, filtering, or sanitization are provided in the documentation to mitigate the risk of malicious instructions being processed by the underlying AI models.
Audit Metadata