emil-design-eng
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-provided UI code (e.g., CSS, JSX), which creates a standard surface for indirect prompt injection. Malicious instructions could be embedded within the code being analyzed to influence the agent's downstream behavior.
- Ingestion points: User-supplied UI code processed during the mandatory
Review Formatworkflow inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when the agent interpolates the user's code into its context.
- Capability inventory: The skill is intended to help build and review interfaces, which in an agent context involves generating code that may be written to the filesystem or executed.
- Sanitization: There are no instructions for the agent to sanitize or filter the user-provided code for potential injection strings before processing.
Audit Metadata