design-md

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the @google/design.md package from the NPM registry using npx. This is the official command-line interface for the DESIGN.md specification hosted by Google.
  • [COMMAND_EXECUTION]: Shell commands (lint, diff, export, spec) are invoked through the CLI tool to process design token files. These operations are performed within the local project context to manage design specifications.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided DESIGN.md files (evidence: SKILL.md under "File anatomy"). While these files contain design data, the use of a formal specification and specialized validation tools (linting) minimizes the risk of the agent misinterpreting embedded instructions as commands.
  • [SAFE]: All external resource references, including the GitHub repository google-labs-code/design.md and the NPM package @google/design.md, originate from a well-known and trusted organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 07:35 PM
Security Audit — agent-trust-hub — design-md