svelte-code-writer

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

• Third-party content exposure detected (high risk: 0.85). The required workflow invokes npx @sveltejs/mcp get-documentation / list-sections, which at runtime fetches Svelte documentation text from an external/public source and feeds it into the agent’s LLM context as readable prose (public web/documentation content).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes runtime npx commands (npx @sveltejs/mcp ...) which will fetch and execute remote package code from the npm registry (e.g., https://registry.npmjs.org/@sveltejs/mcp), meaning external content is executed at runtime and can control prompts/behavior.