agent-svelte-expert
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides expert-level guidance for Svelte 5 and SvelteKit development, specifically emphasizing the use of runes ($state, $derived, $effect) and TypeScript.
- [SAFE]: The skill includes security-focused patterns, such as demonstrating how to set secure HTTP headers (X-Frame-Options, X-Content-Type-Options) in SvelteKit hooks and recommending the use of server-only load functions for sensitive operations involving secrets or database access.
- [SAFE]: The code examples provided for authentication, state management, and form actions follow industry-standard practices, including CSRF protection, secure cookie handling (httpOnly, sameSite, secure), and input validation using Zod.
- [INDIRECT_PROMPT_INJECTION]: The skill includes a
$ARGUMENTSplaceholder at the end ofSKILL.mdto receive user tasks. While this represents a data ingestion surface without explicit boundary markers or sanitization, it is the intended primary purpose for a subagent template within the agent platform and does not introduce malicious behavior or instructions.
Audit Metadata