skills/zx06/xsql/svelte-code-writer/Gen Agent Trust Hub

svelte-code-writer

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Uses npx to fetch and execute the official @sveltejs/mcp package from the NPM registry. This is a standard method for accessing official Svelte development tools.
  • [COMMAND_EXECUTION]: Invokes CLI tools for Svelte documentation management and code analysis within the local environment. The tools provide functionality for listing documentation sections, fetching content, and running code linting.
  • [INDIRECT_PROMPT_INJECTION]: Analyzes user-provided Svelte components and modules. This ingestion of external code is a core function of the skill's autofixing capability.
  • Ingestion points: Processes code or file paths provided via the svelte-autofixer command arguments in SKILL.md.
  • Boundary markers: None (uses standard shell arguments).
  • Capability inventory: Execution of Node.js-based CLI tools via npx across the project filesystem.
  • Sanitization: Instructs the agent to manually escape shell-sensitive characters like $ in runes to prevent local command injection/variable substitution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 04:02 PM
Security Audit — agent-trust-hub — svelte-code-writer