ui-design-system Eval
=====================

Status: failed
Score: 68/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Agent safety gate: This skill should not be selected by an agent without explicit human security review.

Install:
npx skills add majiayu000/spellbook --skill ui-design-system

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Permission surface may require sandboxing
- SKILL.md claims broad capabilities (component architecture, responsive calculations, accessibility compliance, handoff docs) but only provides a token generator script, which may mislead users.
- The script does not directly enforce or validate accessibility constraints; it only generates tokens that could be used for accessibility, but the verification section implies it should validate against accessibility requirements.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 280 stars, 26 forks; issue activity unavailable in current metadata
- Permission surface: secrets or environment access, shell or command execution

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- SKILL.md claims broad capabilities (component architecture, responsive calculations, accessibility compliance, handoff docs) but only provides a token generator script, which may mislead users.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Permission surface may require sandboxing
- The script does not directly enforce or validate accessibility constraints; it only generates tokens that could be used for accessibility, but the verification section implies it should validate against accessibility requirements.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution

URLs:
- Skill: https://www.openagentskill.com/skills/majiayu000-ui-design-system
- Audit: https://www.openagentskill.com/skills/majiayu000-ui-design-system/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=majiayu000-ui-design-system