computer-use

Klasifikasi SUSPICIOUS. Tujuan utama skill cukup selaras dengan analisis data dan otomasi software statistik, tetapi bagian Tier 3 menambahkan instalasi skill eksternal secara transitive trust yang memperluas izin agen ke repositori lain, termasuk satu repo pribadi, tanpa pinning atau verifikasi rilis. Tidak ada bukti eksfiltrasi, pencurian kredensial, atau malware terkonfirmasi, namun rantai pasok dan perluasan trust ini tidak proporsional sebagai fallback otomatis.

This module is not overtly malicious by itself, but it functions as an execution wrapper that can trigger npx-based installation/registration of third-party “skills” based on a user-selected index. The key security concerns are (1) supply-chain risk from running external package manager commands without visible integrity/pinning controls and (2) subprocess.run(..., shell=True) combined with returning/printing stdout/stderr from the invoked process. Review the external artifacts’ trust/integrity controls and consider removing shell=True (use argv list) and minimizing/omitting stdout/stderr in outputs where appropriate.