develop
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill synchronizes UI components using the official '@subframe/cli' package from the npm registry.
- [COMMAND_EXECUTION]: Instructs the agent to run 'npx @subframe/cli sync' to pull design assets into the local project.
- [INDIRECT_PROMPT_INJECTION]: Potential surface for indirect prompt injection through external design data.
- Ingestion points: Design data is fetched via MCP tools like
get_page_info(SKILL.md). - Boundary markers: The skill does not explicitly define delimiters for untrusted content.
- Capability inventory: The agent can execute shell commands (
npx) and modify files in the codebase (SKILL.md). - Sanitization: No sanitization of design tokens or generated code is documented.
- [SAFE]: All external resources, including the MCP server (mcp.subframe.com) and npm packages, belong to the vendor 'subframeapp'.
Audit Metadata