instruments-profiling
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill provides command-line examples for
xcrun xctraceandopen. These are legitimate macOS system utilities used for their intended purpose of application profiling and performance analysis. - DATA_EXPOSURE & EXFILTRATION (SAFE): The skill suggests saving trace data to
/tmp/App.trace. This is a standard location for temporary files and does not involve accessing sensitive user data or transmitting information to external servers. - PROMPT_INJECTION (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found. The language is purely instructional and focused on technical profiling tasks.
- EXTERNAL_DOWNLOADS (SAFE): No external dependencies, scripts, or remote binaries are downloaded or executed.
Audit Metadata