svelte-code-writer

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions using npx @sveltejs/mcp as a command-line entrypoint. This command downloads and executes the MCP server package from the official Svelte organization's registry, which is a well-known and trusted service.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external Svelte source code and documentation, creating a surface for indirect prompt injection where instructions hidden in the files could attempt to override agent behavior.
  • Ingestion points: Processes .svelte, .svelte.ts, and .svelte.js files and fetches external documentation via mcp__svelte__get_documentation.
  • Boundary markers: There are no specific delimiters or "ignore instructions" warnings defined to isolate the content of the processed files from the agent's system instructions.
  • Capability inventory: The skill allows for file creation, modification, and analysis, as well as the execution of the svelte_autofixer tool.
  • Sanitization: No explicit validation or sanitization of the content fetched from files or the documentation tool is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 05:37 AM
Security Audit — agent-trust-hub — svelte-code-writer