design-cli

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text only via an explicitly provided DESIGN.md (e.g., the CLI lint/API lint(markdownString) reads the caller-supplied markdown string/file), so the required workflow can consume arbitrary user text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx to fetch and execute the @google/design.md CLI (e.g., to run "npx @google/design.md spec" which can be used to inject spec context into agent prompts), which obtains remote code from https://www.npmjs.com/package/@google/design.md and therefore introduces a runtime external dependency that can execute code and affect prompts.