image-to-code
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of natural language instructions guiding the agent through a visual design process. It does not include executable code, external dependencies, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied website descriptions to generate code and documentation. While it writes files to the
llmwiki/directory, this is a standard documentation task within a controlled environment and does not involve risky capabilities such as shell execution or external data exfiltration. - [COMMAND_EXECUTION]: The skill mentions common development commands (e.g.,
git log,gh pr diff) in the developer rules but does not instruct the agent to execute arbitrary or dangerous shell commands. No command injection vulnerabilities were found.
Audit Metadata