Skill audit report

Keras audit report.

Deep Learning for humans

REVIEWED · REVIEWSafe to tryGenerated Jun 17, 2026Heuristic metadata audit

Audit

Trust

100

Quality

Security

100

Maintain

Install

OpenAgentSkill Trust Score

Production candidate

Stars, maintenance, license, docs, install safety, permission surface, and installability.

The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

100

64K GitHub stars

Stars/forks activity

PASS

100

64K stars, 20K forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

4d since push

License clarity

PASS

Apache-2.0

README/SKILL.md completeness

INFO

Public metadata needs stronger README/SKILL.md context

Dependency/runtime risk

PASS

no major dependency risk hints in public metadata

Install availability

PASS

npx skills add keras-team/keras

Install command safety

PASS

standard package or runtime install path

Permission surface

PASS

filesystem or document access

Repository evidence

PASS

https://github.com/keras-team/keras

Review status

PASS

AI review data available

Checks

Install and adoption review

11 passed · 1 review

Install path

PASS

npx skills add keras-team/keras

Repository

PASS

https://github.com/keras-team/keras

License

PASS

Apache-2.0

Maintenance

100

PASS

4d since push

AI review

PASS

Approved with no listed issues

README/SKILL.md completeness

PASS

Usable description available

Dependency risk

PASS

no major dependency risk hints in public metadata

Install command safety

PASS

standard package or runtime install path

Permission surface

PASS

filesystem or document access

Stars/forks activity

100

PASS

64K stars, 20K forks; issue activity unavailable in current metadata

Adoption

PASS

64K GitHub stars

Warnings

Documentation summary is thin

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.

Install path

Review the report before installing into production agents.

$ npx skills add keras-team/keras

Signals

Audit score: 96/100
Quality: 100/100
Trust: 96/100
Install safety: 92/100
Permission surface: 86/100
Maintenance: 4d since push
Events: No events yet
GitHub stars: 64K
Last push: Jun 12, 2026

Agent safety v2

80/100 · Review before install

Reviewedreview

Good audit and safety signals with no high-risk permission hints in public metadata.

Review the audit page, then allow agent install in a sandboxed workflow.

Safe-to-try audit
80/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Documentation summary is thin

Back to skill Alternatives Audit badge SVG

Compare nearby options

Related skills to audit next

Tensorflow

An Open Source Machine Learning Framework for Everyone

196K stars · Audit report

Transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

162K stars · Audit report

Pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

101K stars · Audit report