svelte-code-writer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
npxfor the@sveltejs/mcppackage. This allows the agent to fetch documentation and run a Svelte-specific autofixer tool. This is a standard application of official developer tools. - [INDIRECT_PROMPT_INJECTION]: The
svelte-autofixercommand ingests and processes external Svelte component files or raw code strings provided by the user or found in the workspace. - Ingestion points: External files or code blocks passed to
npx @sveltejs/mcp svelte-autofixer(SKILL.md). - Boundary markers: None provided in the command structure to separate code from instructions.
- Capability inventory: The skill has the ability to execute shell commands and read local files.
- Sanitization: There is no explicit sanitization of the content being analyzed by the fixer tool.
Audit Metadata