syncfusion-wpf-ai-assistview
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of a chat UI that processes and displays data from untrusted sources (user input and AI responses). This establishes an attack surface for indirect prompt injection.\n- Ingestion points: Data enters the agent context through the Messages collection in SKILL.md and the PromptRequest event handler in references/events-and-stop-responding.md.\n- Boundary markers: The provided examples do not include explicit delimiters or instructions to ignore embedded commands within the message data.\n- Capability inventory: The skill allows the UI to render content via ViewTemplateSelector (including Markdown) and provides interactive toolbar items for clearing chat or copying text.\n- Sanitization: The documentation focuses on UI implementation and does not detail sanitization or validation procedures for the messages before they are rendered or processed by the AI service.
Audit Metadata