image-to-code
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, patterns, or dangerous commands were detected within the skill's instructions. The content consists entirely of high-level behavioral directives and design configuration parameters.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted user prompts to generate visual designs and frontend code. While this constitutes a standard indirect prompt injection surface, the skill does not grant the agent any dangerous tools, network access, or file system permissions that could be exploited via an injection. The behavior is limited to text and code generation within the agent's standard output context.
Audit Metadata