svelte-code-writer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow invokes pnpx @sveltejs/mcp get-documentation (and potentially list-sections) which fetches Svelte documentation text at runtime from an external source, and that fetched free-form prose is then ingested into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly runs pnpx @sveltejs/mcp at runtime (the npm package @sveltejs/mcp is fetched and executed via pnpx), which executes remote code and is required for the skill’s functionality.