swiftui-expert-skill
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
xctracecommand-line utility to record and export data from Instruments trace files. These operations are performed using thesubprocessmodule with argument lists, which prevents shell injection vulnerabilities by avoiding the use of the shell for command execution. - [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to parse and display log messages and signposts from developer-provided trace files. This creates a surface where external, untrusted data enters the agent's context. This risk is inherent to any log-analysis tool, and the skill mitigates technical risks by using the
defusedxmllibrary to prevent XML-based attacks.
Audit Metadata