design-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to use 'grep' and 'find' for static analysis of SwiftUI source code. These operations are limited to pattern matching within the local project directory and do not involve shell piping to dangerous interpreters or privilege escalation.
- [DATA_EXFILTRATION]: No network-enabled commands or references to external domains were found. The analysis is performed locally on the provided source code.
- [PROMPT_INJECTION]: The skill's instructions focus on structured code review phases and do not contain directives to bypass AI safety guardrails or disclose system prompts.
- [SAFE]: The ingestion of local source code for analysis via 'grep' is a low-risk diagnostic activity that does not expose the system to indirect prompt injection or code execution vulnerabilities as it is performed in a read-only manner.
Audit Metadata