gemini-frontend-design
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Secure Asset Management]: The skill encourages the use of project-relative paths for assets and explicitly advises against hardcoding local filesystem paths, which is a positive security practice to prevent local environment disclosure.
- [Accessibility Compliance]: The instructions mandate adherence to WCAG contrast standards and system motion preferences, ensuring the generated content is safe and accessible for all users.
- [Indirect Prompt Injection Surface]: The skill ingests untrusted user-supplied briefs and text in SKILL.md. This represents a potential surface where malicious instructions embedded in user data could influence agent behavior. While no explicit sanitization or boundary markers are defined, the skill focuses on faithful content reproduction and contains no dangerous command execution capabilities.
Audit Metadata