svelte-code-writer

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and executes the @sveltejs/mcp package from the official npm registry. This is an official utility provided by the Svelte project for documentation and context protocol support.
  • [COMMAND_EXECUTION]: Utilizes npx to run CLI commands for documentation retrieval and code analysis. The instructions include security best practices for escaping shell characters.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it processes external Svelte code through the autofixer utility.
  • Ingestion points: Processes arbitrary code strings or local files via the svelte-autofixer command defined in SKILL.md.
  • Boundary markers: No explicit output delimiters or isolation instructions are defined for the agent.
  • Capability inventory: Executes shell-based developer tools (npx).
  • Sanitization: Instructs the user to escape the $ sign to prevent shell command injection or expansion.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:51 PM
Security Audit — agent-trust-hub — svelte-code-writer