Skill audit report

CascadePSP Audit report.

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

REVIEWED · REVIEWNeeds reviewGenerated Aug 3, 2026Heuristic metadata audit
78
Audit
79
Trust
73
Quality
87
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

885 GitHub stars

Stars/forks activity

INFO

71

885 stars, 97 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

62

7mo since push

License clarity

PASS

86

MIT

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 hkchengrex/CascadePSP

Install command safety

PASS

92

standard package or runtime install path

Permission surface

INFO

72

filesystem or document access, network or browser access

Repository evidence

PASS

86

https://github.com/hkchengrex/CascadePSP

Review status

PASS

88

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

8 Passed · 4 Needs review

Install path

92

PASS

npx skills add hkchengrex/CascadePSP

Repository

88

PASS

https://github.com/hkchengrex/CascadePSP

License

86

PASS

MIT

Maintenance

62

CHECK

7mo 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

72

CHECK

filesystem or document access, network or browser access

Stars/forks activity

71

CHECK

885 stars, 97 forks; issue activity unavailable in current metadata

Adoption

88

PASS

885 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.

Compare nearby options

Related skills to audit next