ai-sdk-ui
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface (XSS). The skill contains documentation and commented-out code segments (in
references/streaming-patterns.mdandtemplates/custom-message-renderer.tsx) that suggest using 'dangerouslySetInnerHTML' to render content directly from the AI. - Ingestion points: AI message content processed by the
useChathook and history loaded fromlocalStorage(intemplates/message-persistence.tsx). - Boundary markers: No explicit delimiters or instruction-ignoring warnings are present in the rendering logic.
- Capability inventory: Browser-side DOM manipulation and script execution.
- Sanitization: The provided patterns do not include HTML sanitization (e.g., DOMPurify), making the resulting UI vulnerable to XSS if an attacker performs indirect prompt injection through external data sources.
- [EXTERNAL_DOWNLOADS] (SAFE): The utility script
scripts/check-versions.shusesnpm viewto fetch version information. This is a standard developmental tool and does not constitute a remote code execution risk in this context.
Audit Metadata