emil-design-eng
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and review UI code provided by users, which creates a surface for malicious instructions to be embedded within the data.
- Ingestion points: The skill processes untrusted code snippets provided by the user for review.
- Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions hidden within the code comments or content being reviewed.
- Capability inventory: The skill is limited to providing text-based reviews and design advice; it does not have access to the shell, file system, or network tools.
- Sanitization: There are no instructions provided for the agent to sanitize or filter the input code before processing it.
Audit Metadata