ios-design
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill files. The content is purely educational and instructional.
- [PROMPT_INJECTION]: No override instructions or jailbreak attempts were found. The skill maintains its intended role as a design and code auditor.
- [DATA_EXFILTRATION]: No hardcoded secrets, sensitive file path access, or unauthorized network communications were identified. External URLs point to official Apple documentation and reputable open-source repositories.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified third-party dependencies.
- [COMMAND_EXECUTION]: The skill contains example bash and grep commands in its reference documents; however, these are presented as tools for a user to run locally on their own source code for auditing purposes, not for autonomous execution by the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied code snippets for review. While this constitutes an attack surface, the risk is mitigated as the skill only provides descriptive critiques and does not attempt to execute or dynamically interpret the user data.
Audit Metadata