Laporan audit skill

apu-memory-tuner Laporan audit.

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the CPU. Use when the user mentions Ryzen AI, Strix Halo / Strix Point / Krackan / Phoenix / Hawk Point, Ryzen AI Max, gfx1150 / gfx1151 / gfx1152, integrated Radeon, iGPU memory, UMA Frame Buffer Size, AMD Variable Graphics Memory, VGM, GTT, GART, TTM, pages_limit, amd-ttm, amd-debug-tools, "shared GPU memory", "dedicated GPU memory", carve-out, "not enough VRAM", "out of VRAM", "GPU OOM", llama.cpp on iGPU, ROCm on APU; or asks how much memory the iGPU can use, how to give the iGPU more memory, how to balance memory between CPU and GPU on UMA, or how to change the BIOS UMA reservation. Read-only diagnostics work everywhere; tuning runs automatically on Linux via `amd-ttm` and prints guided BIOS steps on Windows. Do not use for discrete Radeon cards, Intel iGPUs, or Apple Silicon -- it is APU-o

Diblokir · BlokirPerlu ditinjauDihasilkan 13 Okt 2026Audit metadata heuristik
77
Audit
74
Kepercayaan
69
Kualitas
79
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

74
Shortlist kuat

Trust Score OpenAgentSkill

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

Adopsi GitHub

Info

62

332 star GitHub

Aktivitas star/fork

Peringatan

57

332 star dan 30 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

88

1 bulan sejak push

Kejelasan lisensi

Lulus

86

MIT

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Peringatan

54

command execution surface, credential or environment access

Ketersediaan pemasangan

Lulus

92

npx skills add amd/skills --skill apu-memory-tuner

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Peringatan

50

secrets or environment access, shell or command execution

Bukti repositori

Lulus

86

https://github.com/amd/skills/tree/main/staging/apu-memory-tuner

Status peninjauan

Lulus

88

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

54

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

7 Lulus · 13 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add amd/skills --skill apu-memory-tuner

Repositori

88

Lulus

https://github.com/amd/skills/tree/main/staging/apu-memory-tuner

Lisensi

86

Lulus

MIT

Pemeliharaan

88

Lulus

1 bulan sejak push

Tinjauan AI

88

Lulus

Approved with no listed issues

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

54

Perbaiki

command execution surface, credential or environment access

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

50

Perbaiki

secrets or environment access, shell or command execution

Aktivitas star/fork

57

Perbaiki

332 star dan 30 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

68

Info

332 star GitHub

Financial decision safety

58

Periksa

Research-only use: do not treat output as financial advice or execute a position without human approval.

Peringatan

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Financial research output is not financial advice; require human review before any live investment decision
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Stars/forks activity: 332 stars, 30 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution

Metode

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Bandingkan opsi sekitar

Skill terkait untuk diaudit berikutnya