image-to-code
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text guiding an AI agent through a creative web design process. No scripts, network requests, or attempts to access sensitive local data were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided design descriptions to generate images and code. While this creates a surface for potential prompt injection, the risk is inherent to the skill's purpose and no dangerous tools are leveraged.
- Ingestion points: User descriptions of websites provided in the agent interaction context.
- Boundary markers: Absent; no delimiters or instructions for isolating untrusted data.
- Capability inventory: Image generation and frontend code implementation.
- Sanitization: Absent; no instructions for input validation or content filtering.
Audit Metadata