Skill 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.
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
PASS100
42K GitHub stars
Stars/forks activity
PASS97
42K stars, 3.0K forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
10d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
WARN54
command execution surface, external package install surface
Install availability
PASS92
npx skills add alibaba/open-code-review --skill open-code-review-delegate
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL36
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/alibaba/open-code-review/tree/main/skills/open-code-review-delegate
Review status
WARN50.37
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add alibaba/open-code-review --skill open-code-review-delegate
Repository
88
https://github.com/alibaba/open-code-review/tree/main/skills/open-code-review-delegate
License
86
Apache-2.0
Maintenance
100
10d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
86
Usable description available
Dependency risk
54
command execution surface, external package install surface
Install command safety
92
standard package or runtime install path
Permission surface
36
shell or command execution, filesystem or document access
Stars/forks activity
97
42K stars, 3.0K forks; issue activity unavailable in current metadata
Adoption
88
42K GitHub stars
Warnings
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.