svelte-design

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted user input to generate frontend code, creating a surface for potential instruction injection. * Ingestion points: User-provided frontend requirements for components or applications. * Boundary markers: Absent; there are no specific instructions or delimiters used to isolate user-provided requirements from the agent instructions. * Capability inventory: The skill generates Svelte/SvelteKit code and coordinates with other skills like shadcn-svelte-management. * Sanitization: Absent; the skill does not specify validation or sanitization steps for user-provided data before it is incorporated into code generation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 09:22 PM