imagegen Eval report.

Task wording matches this skill metadata.

• Evaluate imagegen before installing it in an agent workflow
• design-creative
• Design and creative workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add yan-labs/yan-skills --skill imagegen

standard package or runtime install path

• npx skills add yan-labs/yan-skills --skill imagegen

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 177 GitHub stars
• MIT

Needs review

• The skill mandates the use of `--sandbox danger-full-access`, which is a high-risk permission level. While justified for network access, it should be used with caution and only in trusted environments.

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

• Test manually in an isolated workspace and compare against safer alternatives.
• High-risk permission hints: Shell or command execution

MIT

• MIT

shell or command execution, filesystem or document access

• Shell or command execution: high
• Network access: medium
• Filesystem access: medium