ksp
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script ('scripts/inspect-project.py') and instructs the agent to execute it locally using 'python3'. The script is used to analyze the project's Gradle configuration, Kotlin/Java source files, and service registrations to verify the KSP setup. It uses only standard Python libraries (e.g., tomllib, re, argparse) and does not perform any network operations.- [SAFE]: The project inspection is conducted entirely locally. No external packages are installed at runtime, and there is no evidence of remote code execution from untrusted sources. All URLs referenced in the documentation point to official documentation for Kotlin and KSP (google/ksp and kotlinlang.org).
Audit Metadata