emil-design-eng
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains behavioral instructions to restrict the initial response format, which is a common and benign practice for setting agent personas. There are no attempts to bypass safety filters or disregard system instructions.
- [DATA_EXFILTRATION]: No sensitive file paths, credential patterns, or suspicious network operations were detected. The skill references legitimate design resources such as animations.dev, easing.dev, and easings.co.
- [EXTERNAL_DOWNLOADS]: The skill does not perform or instruct any external code downloads or package installations. It provides CSS and JavaScript code snippets as examples for the user's reference.
- [COMMAND_EXECUTION]: There are no instructions to execute shell commands or interact with the underlying operating system in a way that poses a security risk.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided UI code for review, it does not possess dangerous capabilities (such as file writing or network access) that could be exploited by malicious content embedded in the ingested code. The interaction is limited to providing design feedback in a structured markdown table.
Audit Metadata