Skills
Navigate
skills/syncfusion/javascript-ui-controls-skills/syncfusion-javascript-ai-assistview/Gen Agent Trust Hub

syncfusion-javascript-ai-assistview

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides building blocks for an AI assistant interface that processes and renders data from external AI providers, creating a potential surface for indirect prompt injection.
  • Ingestion points: The component ingests data from external AI services via the promptRequest event and addPromptResponse method as described in SKILL.md and references/ai-integrations.md.
  • Boundary markers: The provided implementation examples do not include explicit boundary markers or instructions to the model to ignore embedded commands within the response data.
  • Capability inventory: The documentation demonstrates capabilities such as network requests (fetch calls to AI APIs in references/ai-integrations.md) and dynamic UI rendering through templates and registerToolUI in references/generative-ui.md.
  • Sanitization: While the examples suggest using the marked library to parse markdown in references/ai-integrations.md, they do not demonstrate specific XSS sanitization for the final HTML output, which is a common requirement when rendering third-party AI content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 10:55 PM
Security Audit — agent-trust-hub — syncfusion-javascript-ai-assistview