Laporan audit skill

redteam Laporan audit.

Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.

Eksperimental · TinjauPerlu ditinjauDihasilkan 13 Okt 2026Audit metadata heuristik
76
Audit
70
Kepercayaan
70
Kualitas
76
Keamanan
88
Maintain
92
Pasang

Trust Score OpenAgentSkill

70
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

76

816 star GitHub

Aktivitas star/fork

Info

71

816 star dan 65 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

88

2 bulan sejak push

Kejelasan lisensi

Lulus

86

Apache-2.0

Kelengkapan README/SKILL.md

Lulus

86

Metadata memuat konteks penggunaan dan alur kerja yang cukup

Risiko dependensi/runtime

Info

64

command execution surface, database surface

Ketersediaan pemasangan

Lulus

92

npx skills add agentscope-ai/OpenJudge --skill redteam

Keamanan perintah pemasangan

Lulus

92

Jalur pemasangan paket atau runtime standar

Cakupan izin

Peringatan

50

shell or command execution, filesystem or document access

Bukti repositori

Lulus

86

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/07-redteam

Status peninjauan

Info

66

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 agentscope-ai/OpenJudge --skill redteam

Repositori

88

Lulus

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/07-redteam

Lisensi

86

Lulus

Apache-2.0

Pemeliharaan

88

Lulus

2 bulan sejak push

Tinjauan AI

55

Periksa

The script assumes a specific JSONL schema for attack and over-refusal rows; while documented, it could be more flexible or provide validation errors for malformed input.

Kelengkapan README/SKILL.md

86

Lulus

Usable description available

Risiko dependensi

64

Periksa

command execution surface, database surface

Keamanan perintah pemasangan

92

Lulus

Jalur pemasangan paket atau runtime standar

Cakupan izin

50

Perbaiki

shell or command execution, filesystem or document access

Aktivitas star/fork

71

Periksa

816 star dan 65 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Adopsi

88

Lulus

816 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

  • Permission surface may require sandboxing
  • Financial research output is not financial advice; require human review before any live investment decision
  • The script assumes a specific JSONL schema for attack and over-refusal rows; while documented, it could be more flexible or provide validation errors for malformed input.
  • The SKILL.md excerpt is truncated in the review, but the visible content is thorough; the full file likely covers all steps.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Permission surface: shell or command execution, filesystem or document 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