Laporan audit skill

alterlab-alphafold Laporan audit.

Predict protein 3D structures with AlphaFold2 via ColabFold — MMseqs2-accelerated MSAs, monomer and AlphaFold2-Multimer complex folding, and confidence-based validation (pLDDT, pTM/ipTM, PAE). Use when folding a protein sequence or complex from FASTA, generating a predicted structure with confidence metrics, ranking models, or checking self-consistency of a design. For co-folding a protein WITH a small-molecule ligand or predicting binding affinity prefer alterlab-boltz; for antibody–antigen or one-FASTA multi-entity complexes prefer alterlab-chai; to LOOK UP an already-computed structure prefer alterlab-alphafold-db; for ESM embeddings or inverse folding prefer alterlab-esm. Part of the AlterLab Academic Skills suite.

Eksperimental · TinjauPerlu ditinjauDihasilkan 13 Okt 2026Audit metadata heuristik
71
Audit
63
Kepercayaan
62
Kualitas
74
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

63
Tinjauan manual

Trust Score OpenAgentSkill

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

Adopsi GitHub

Peringatan

48

66 star GitHub

Aktivitas star/fork

Peringatan

48

66 star dan 13 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

56

command execution surface, network or browser surface

Ketersediaan pemasangan

Lulus

92

npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-alphafold

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Peringatan

50

shell or command execution, network or browser access

Bukti repositori

Lulus

86

https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/tree/main/skills/bioinformatics/alterlab-alphafold

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 · 16 Perlu ditinjau

Jalur pemasangan

92

Lulus

npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-alphafold

Repositori

88

Lulus

https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/tree/main/skills/bioinformatics/alterlab-alphafold

Lisensi

86

Lulus

MIT

Pemeliharaan

88

Lulus

1 bulan sejak push

Tinjauan AI

55

Periksa

allowed-tools grants unrestricted Bash(python:*) and Bash(uv:*), which permits arbitrary code execution; this is broad even if common for bioinformatics tooling.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

56

Perbaiki

command execution surface, network or browser surface

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

50

Perbaiki

shell or command execution, network or browser access

Aktivitas star/fork

48

Perbaiki

66 star dan 13 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

68

Info

66 star GitHub

Peringatan

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • allowed-tools grants unrestricted Bash(python:*) and Bash(uv:*), which permits arbitrary code execution; this is broad even if common for bioinformatics tooling.
  • SKILL.md contains TODO(verify) placeholders for exact ColabFold installation pins and flag names, reducing reproducibility and clarity for agent execution.
  • The MSA step sends sequences to a public MMseqs2 API by default; the skill mentions disclosure for sensitive sequences but does not enforce or strongly gate this in the workflow.
  • Setup instructions are incomplete: no exact package version, CUDA/JAX pin, or verified command sequence is provided for installing and running ColabFold.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, network or browser access
  • GitHub adoption: 66 GitHub stars
  • Stars/forks activity: 66 stars, 13 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, network or browser surface
  • Permission surface: shell or command execution, network or browser access

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