Laporan audit skill
docx Laporan audit.
Extract text from Microsoft Word documents
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adopsi GitHub
Lulus86
1.5K star GitHub
Aktivitas star/fork
Info77
1.5K star dan 143 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Pemeliharaan terbaru
Lulus100
14 hari sejak push
Kejelasan lisensi
Lulus86
AGPL-3.0-or-later
Kelengkapan README/SKILL.md
Info70
Metadata publik memerlukan konteks README/SKILL.md yang lebih kuat
Risiko dependensi/runtime
Info62
command execution surface, external package install surface
Ketersediaan pemasangan
Lulus92
npx skills add axoviq-ai/synthadoc --skill docx
Keamanan perintah pemasangan
Lulus92
Jalur pemasangan paket atau runtime standar
Cakupan izin
Info62
shell or command execution, filesystem or document access
Bukti repositori
Lulus86
https://github.com/axoviq-ai/synthadoc/tree/main/synthadoc/skills/docx
Status peninjauan
Info66
Data tinjauan AI tersedia
Hasil terbukti Agent
Info54
Belum ada data hasil Agent
Pemeriksaan
Tinjauan pemasangan dan adopsi
Jalur pemasangan
92
npx skills add axoviq-ai/synthadoc --skill docx
Repositori
88
https://github.com/axoviq-ai/synthadoc/tree/main/synthadoc/skills/docx
Lisensi
86
AGPL-3.0-or-later
Pemeliharaan
100
14 hari sejak push
Tinjauan AI
55
SKILL.md does not mention that extracted Word document content should be treated as untrusted data, which is relevant for agents that might interpret document text as instructions.
Kelengkapan README/SKILL.md
84
Usable description available
Risiko dependensi
62
command execution surface, external package install surface
Keamanan perintah pemasangan
92
Jalur pemasangan paket atau runtime standar
Cakupan izin
62
shell or command execution, filesystem or document access
Aktivitas star/fork
77
1.5K star dan 143 fork; aktivitas issue tidak tersedia dalam metadata saat ini
Adopsi
88
1.5K star GitHub
Peringatan
- SKILL.md does not mention that extracted Word document content should be treated as untrusted data, which is relevant for agents that might interpret document text as instructions.
- SKILL.md documents paragraph extraction but does not note that tables, headers, footers, and text boxes are ignored.
- No guidance on handling unusually large or malformed .docx files; python-docx parsing can consume significant memory if given a crafted or zip-bomb-like document.
- Quality score needs review
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