Skill audit report

Light A Video Audit report.

[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion

REVIEWED · REVIEWNeeds reviewGenerated Aug 3, 2026Heuristic metadata audit
76
Audit
79
Trust
66
Quality
89
Security
62
Maintain
92
Install

OpenAgentSkill Trust Score

79
Strong shortlist

OpenAgentSkill Trust Score

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

GitHub adoption

INFO

76

514 GitHub stars

Stars/forks activity

INFO

65

514 stars, 34 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

62

9mo since push

License clarity

PASS

86

Apache-2.0

README/SKILL.md completeness

PASS

90

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add bcmi/Light-A-Video

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

86

filesystem or document access

Repository evidence

PASS

86

https://github.com/bcmi/Light-A-Video

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

9 Passed · 3 Needs review

Install path

92

PASS

npx skills add bcmi/Light-A-Video

Repository

88

PASS

https://github.com/bcmi/Light-A-Video

License

86

PASS

Apache-2.0

Maintenance

62

CHECK

9mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

90

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

86

PASS

filesystem or document access

Stars/forks activity

65

CHECK

514 stars, 34 forks; issue activity unavailable in current metadata

Adoption

88

PASS

514 GitHub stars

Warnings

  • Quality score needs review

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.