SwiftUI Codegen Expert
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill contains only instructional prompts for code generation and does not attempt to override the underlying AI safety filters or system instructions.- Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network transmission patterns were identified.- Obfuscation (SAFE): The markdown content is entirely in plain text with no hidden characters, encoding, or deceptive formatting.- Indirect Prompt Injection (LOW): The skill is designed to ingest external data such as screenshots and design files which could theoretically contain malicious instructions. 1. Ingestion points: screenshots, Stitch design paths. 2. Boundary markers: absent. 3. Capability inventory: Read, Edit, Bash, WebFetch. 4. Sanitization: none mentioned.- Unverifiable Dependencies (SAFE): The skill does not define any external packages (npm, pip) or execute remote scripts.
Audit Metadata