frontend-design
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (HIGH): The skill instructs the agent to scan untrusted codebases for design patterns. This external content acts as a vector for malicious instructions.
- [Evidence]:
- Ingestion points: Scanning layout patterns, typography hierarchy, and component structure in existing codebases.
- Boundary markers: None specified to differentiate code-as-data from instructions.
- Capability inventory: Building components, pages, applications, design systems, and UI modifications.
- Sanitization: None described for the ingested external content.
Recommendations
- AI detected serious security threats
Audit Metadata