svelte-code-writer
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the
@sveltejs/mcppackage from the official Svelte organization using thenpxcommand. This is a standard and safe practice for providing documentation and tooling. - [INDIRECT_PROMPT_INJECTION]: The
svelte-autofixertool processes external Svelte components and code blocks, which can contain malicious instructions intended to influence the agent. 1. Ingestion points: Code strings or file paths provided to the tool via the command line. 2. Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded content. 3. Capability inventory: Use is restricted to code analysis with no high-privilege capabilities exposed. 4. Sanitization: No sanitization is performed on input code.
Audit Metadata