Skill audit report

open-code-review-delegate Audit report.

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Aug 24, 2026Heuristic metadata audit
85
Audit
75
Trust
91
Quality
75
Security
100
Maintain
92
Install

OpenAgentSkill Trust Score

75
Strong shortlist

OpenAgentSkill Trust Score

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

GitHub adoption

PASS

100

21K GitHub stars

Stars/forks activity

PASS

97

21K stars, 1.6K forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

Pushed today

License clarity

PASS

86

Apache-2.0

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

WARN

54

command execution surface, external package install surface

Install availability

PASS

92

npx skills add alibaba/open-code-review --skill open-code-review-delegate

Install command safety

PASS

92

standard package or runtime install path

Permission surface

WARN

48

shell or command execution, filesystem or document access

Repository evidence

PASS

86

https://github.com/alibaba/open-code-review/tree/main/skills/open-code-review-delegate

Review status

INFO

66

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

8 Passed · 11 Needs review

Install path

92

PASS

npx skills add alibaba/open-code-review --skill open-code-review-delegate

Repository

88

PASS

https://github.com/alibaba/open-code-review/tree/main/skills/open-code-review-delegate

License

86

PASS

Apache-2.0

Maintenance

100

PASS

Pushed today

AI review

55

CHECK

The SKILL.md excerpt is truncated at the end, but the provided content is clear and complete for the described workflow.

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

54

FIX

command execution surface, external package install surface

Install command safety

92

PASS

standard package or runtime install path

Permission surface

48

FIX

shell or command execution, filesystem or document access

Stars/forks activity

97

PASS

21K stars, 1.6K forks; issue activity unavailable in current metadata

Adoption

88

PASS

21K GitHub stars

Warnings

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The SKILL.md excerpt is truncated at the end, but the provided content is clear and complete for the described workflow.
  • No explicit security guidance for handling untrusted repository content or user-supplied arguments to `ocr` commands, though this is standard for code review tools.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Dependency/runtime risk: command execution surface, external package install surface
  • Permission surface: shell or command execution, filesystem or document access

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