design-system
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities detected. The skill operates as intended for design auditing.
- [DATA_EXFILTRATION]: No exfiltration patterns found. The skill reads local styling files and uses a browser tool to research competitor sites as part of its core design generation logic.
- [COMMAND_EXECUTION]: No unauthorized command execution or privilege escalation attempts were found in the instructions.
- [PROMPT_INJECTION]: The skill does not contain instructions to bypass safety filters or override agent behavior.
- [DATA_EXPOSURE_&_EXFILTRATION]: The skill presents an indirect prompt injection surface because it processes data from external websites and local files.
- Ingestion points: Local CSS/JS source code and external website content via browser MCP.
- Boundary markers: Absent.
- Capability inventory: Reading local files, navigating to external URLs, and writing output files (HTML/JSON/MD).
- Sanitization: None documented.
Audit Metadata