Laporan audit skill

rocm-doctor Laporan audit.

Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux or Windows, then applies a low-risk fix with consent or hands back the exact next step. Also routes Lemonade, LM Studio, and Ollama problems to the right upstream channel. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, or hits hipErrorNoBinaryForGpu, HSA_STATUS_ERROR_INVALID_ISA, "invalid device function", "no kernel image is available", cannot open /dev/kfd, permission denied on /dev/kfd, "ROCk module is NOT loaded", a missing libamdhip64.so / amdhip64_6.dll / hipblas.dll / vcruntime140_1.dll, an HSA_OVERRIDE_GFX_VERSION page fault, an iGPU+dGPU crash, a container that can't see the GPU, or an amdgpu-install / DKMS failure. Backed by the `rocm` CLI (`rocm examine` / `rocm diagnose` / `rocm fix`); this skill is a thin driver over those commands, not a re-implementation.

Diblokir · BlokirPerlu ditinjauDihasilkan 13 Okt 2026Audit metadata heuristik
73
Audit
65
Kepercayaan
69
Kualitas
71
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

65
Tinjauan manual

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

44

command execution surface, credential or environment access

Ketersediaan pemasangan

Lulus

92

npx skills add amd/skills --skill rocm-doctor

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Gagal

36

secrets or environment access, shell or command execution

Bukti repositori

Lulus

86

https://github.com/amd/skills/tree/main/staging/rocm-doctor

Status peninjauan

Info

66

Data tinjauan AI tersedia

Hasil terbukti Agent

Info

54

Belum ada data hasil Agent

Pemeriksaan

Tinjauan pemasangan dan adopsi

6 Lulus · 13 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add amd/skills --skill rocm-doctor

Repositori

88

Lulus

https://github.com/amd/skills/tree/main/staging/rocm-doctor

Lisensi

86

Lulus

MIT

Pemeliharaan

88

Lulus

1 bulan sejak push

Tinjauan AI

55

Periksa

The installation method uses curl | sh / irm | iex, which is a common but potentially risky pattern. While consent is required, it would be safer to recommend a manual download or checksum verification.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

44

Perbaiki

command execution surface, credential or environment access

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

36

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

Peringatan

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The installation method uses curl | sh / irm | iex, which is a common but potentially risky pattern. While consent is required, it would be safer to recommend a manual download or checksum verification.
  • The skill depends entirely on the `rocm` CLI being installed; if the CLI cannot be installed or is unavailable, the skill stops without providing any fallback guidance.
  • 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