emil-design-eng
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a persona and specific design rules for reviewing UI code. It does not contain executable scripts, external dependencies, or network-enabled tools.
- [PROMPT_INJECTION]: The skill uses behavioral constraints (e.g., 'Do not provide any other information until the user asks a question') and a mandatory output format (markdown table) to maintain its persona. These are standard alignment instructions and do not represent attempts to bypass security filters or override agent safety protocols.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or data exfiltration logic were found. The external links provided (e.g., animations.dev, easing.dev) are legitimate design resources related to the skill's purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data because its primary function is to review user-provided UI code. However, the skill possesses no capabilities for code execution, file modification, or network requests, which significantly limits the risk of an indirect prompt injection attack.
Audit Metadata