Skill audit report

auto-arena Audit report.

Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.

BLOCKED · BLOCKRiskyGenerated Nov 3, 2026Heuristic metadata audit

Audit

Trust

Quality

Security

Maintain

Install

OpenAgentSkill Trust Score

Manual review

OpenAgentSkill Trust Score

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

GitHub adoption

INFO

809 GitHub stars

Stars/forks activity

INFO

809 stars, 65 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

3mo since push

License clarity

PASS

Apache-2.0

README/SKILL.md completeness

PASS

Metadata includes enough usage and workflow context

Dependency/runtime risk

FAIL

command execution surface, credential or environment access

Install availability

PASS

npx skills add agentscope-ai/OpenJudge --skill auto-arena

Install command safety

PASS

standard package or runtime install path

Permission surface

FAIL

secrets or environment access, shell or command execution

Repository evidence

PASS

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/auto-arena

Review status

PASS

AI review data available

Agent Proven outcomes

INFO

No agent outcome data yet

Checks

Install and adoption review

7 Passed · 12 Needs review

Install path

PASS

npx skills add agentscope-ai/OpenJudge --skill auto-arena

Repository

PASS

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/auto-arena

License

PASS

Apache-2.0

Maintenance

CHECK

3mo since push

AI review

PASS

Approved with no listed issues

README/SKILL.md completeness

PASS

Usable description available

Dependency risk

FIX

command execution surface, credential or environment access

Install command safety

PASS

standard package or runtime install path

Permission surface

FIX

secrets or environment access, shell or command execution

Stars/forks activity

CHECK

809 stars, 65 forks; issue activity unavailable in current metadata

Adoption

PASS

809 GitHub stars

Warnings

Dependency or permission surface needs review
Permission surface may require sandboxing
Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
Quality score needs review
Permission surface needs review: secrets or environment access, shell or command execution
Dependency/runtime risk: command execution surface, credential or environment access
Permission surface: secrets or environment access, shell or command execution

Method

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.

Install path

Review the report before installing into production agents.

$ npx skills add agentscope-ai/OpenJudge --skill auto-arena

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: block
Best agents: Codex + Claude Code
Alternatives: 3

Open agent JSON

Signals

Audit score: 74/100
Quality: 70/100
Trust: 71/100
Install safety: 92/100
Permission surface: 18/100
Maintenance: 3mo since push
Events: 9 events
GitHub stars: 809
Last push: Aug 3, 2026

Agent safety v2

30/100 · Avoid automatic install

Blocked for auto-installblock

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

Audit risk exceeds the requested agent policy
Audit classified this skill as risky
Metadata combines secrets access with shell or command execution
Audit risk risky exceeds max_risk=medium

Shell or command execution

high

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Secrets or environment access

high

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

Audit risk risky exceeds max_risk=medium
High-risk permission hints: Shell or command execution, Secrets or environment access
Dependency or permission surface needs review

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Echarts

Apache ECharts is a powerful, interactive charting and data visualization library for browser

67K Stars · Audit report

D3

Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:

113K Stars · Audit report

Scientific Agent Skills

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

33K Stars · Audit report