ui-redesign
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The analyzed skill contains purely instructional content focused on design standards, typography, color theory, and code quality. It does not contain executable scripts, obfuscated code, or sensitive data exposure.- [EXTERNAL_DOWNLOADS]: The skill references picsum.photos as a source for placeholder background images. This is a well-known and reputable service commonly used in web development.- [PROMPT_INJECTION]: The skill defines a workflow that involves reading external codebases (Ingestion point: SKILL.md 'Scan' phase) and modifying them (Capability: SKILL.md 'Fix' phase). This creates an indirect prompt injection surface where instructions hidden within a user's codebase could potentially influence agent behavior. No boundary markers or sanitization methods are specified in the instructions to mitigate this inherent risk associated with the skill's primary purpose.
Audit Metadata