frontend-design
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected across the skill's instructions or reference files. The content is strictly limited to design guidance, implementation principles, and user experience best practices.\n- [DATA_EXPOSURE]: The skill uses a protocol to read a configuration file (
.impeccable.md) from the project root to gather design context. This is a standard and safe method for tailoring agent output to specific project needs without accessing sensitive system data or credentials.\n- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external data from the.impeccable.mdfile to determine target audience and brand personality. This ingestion point is low-risk and intended for design parameterization.\n - Ingestion points: Reads project-specific design context from
.impeccable.md.\n - Boundary markers: None explicitly defined in the file reading instruction, though it specifies required fields (audience, use cases, tone).\n
- Capability inventory: The skill generates frontend code and utilizes an internal command (
/teach-impeccable) for interactive context gathering.\n - Sanitization: No explicit sanitization is described, as the data is used to inform creative direction rather than being executed as code.
Audit Metadata