emil-design-eng
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided UI code and project design tokens for review and implementation tasks. This creates a surface where instructions embedded in external code could potentially influence the agent's actions. \n
- Ingestion points: Analysis of UI code and design configurations as described in
SKILL.mdand the detailed guide. \n - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard content within the reviewed code. \n
- Capability inventory: The skill facilitates modification of components and implementation of animations, which may utilize file system tools if available to the agent. \n
- Sanitization: No input validation or sanitization of analyzed code is specified. \n- [SAFE]: No evidence of data exfiltration, malicious code execution, or credential harvesting was found. The skill's technical instructions are consistent with industry-standard frontend engineering practices.
Audit Metadata