Skill audit report

paper-review Audit report.

Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.

BLOCKED · BLOCKNeeds reviewGenerated Nov 5, 2026Heuristic metadata audit
72
Audit
65
Trust
70
Quality
70
Security
76
Maintain
92
Install

OpenAgentSkill Trust Score

65
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

76

816 GitHub stars

Stars/forks activity

INFO

71

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

Recent maintenance

INFO

76

3mo since push

License clarity

PASS

86

Apache-2.0

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

FAIL

36

command execution surface, credential or environment access

Install availability

PASS

92

npx skills add agentscope-ai/OpenJudge --skill paper-review

Install command safety

PASS

92

standard package or runtime install path

Permission surface

FAIL

22

secrets or environment access, shell or command execution

Repository evidence

PASS

86

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review

Review status

INFO

66

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

6 Passed · 13 Needs review

Install path

92

PASS

npx skills add agentscope-ai/OpenJudge --skill paper-review

Repository

88

PASS

https://github.com/agentscope-ai/OpenJudge/tree/main/skills/paper-review

License

86

PASS

Apache-2.0

Maintenance

76

CHECK

3mo since push

AI review

55

CHECK

Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

36

FIX

command execution surface, credential or environment access

Install command safety

92

PASS

standard package or runtime install path

Permission surface

22

FIX

secrets or environment access, shell or command execution

Stars/forks activity

71

CHECK

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

Adoption

88

PASS

816 GitHub stars

Warnings

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Inconsistency between SKILL.md and reference.md regarding vision mode default: SKILL.md says --vision is on by default, while reference.md lists use_vision_for_pdf default as False. This could confuse users about whether pypdfium2 is required by default.
  • The skill requires API keys and external API calls (LiteLLM, CrossRef, arXiv, DBLP), which may raise privacy or cost concerns, but these are standard for such tools and clearly documented.
  • 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.

Compare nearby options

Related skills to audit next