argent-native-profiler
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external data produced by profiling tools (iOS xctrace and Android Perfetto) and reading native source code. This represents a potential ingestion point for untrusted data. However, the data processed (stack traces, function names, performance metrics) is technical in nature, and the skill includes specific investigation patterns to guide the agent, minimizing the risk of accidental instruction following from the analyzed data.
- [COMMAND_EXECUTION]: The skill utilizes native profiling utilities and device interaction tools. These are standard development operations required for the skill's stated purpose of performance analysis and do not involve suspicious or unauthorized command execution.
- [SAFE]: The workflow describes standard performance debugging procedures, including starting/stopping recordings, analyzing hotspots, and comparing sessions. All referenced tools and behaviors align with the intended developer-centric use case.
Audit Metadata